ResidualDroppath: Enhancing Feature Reuse over Residual Connections | Paper Citation Record

Observation 262943c6-9f7a-42b0-b2c8-7a7dcafc036f · outbound

This paper cites Layer by layer: Uncovering where multi-task learning happens in instruction-tuned large language mod- els.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Layer by layer: Uncovering where multi-task learning happens in instruction-tuned large language mod- els

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.169375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b60667-fda0-4fd5-aaf9-5dc15d69d831 · outbound

This paper cites Understanding and improving features learned in deep functional maps.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Understanding and improving features learned in deep functional maps

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.174121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e660ee1-838f-4ee1-8340-edec0c406baf · outbound

This paper cites Information complexity of stochastic convex optimization: Applications to generaliza- tion, memorization, and tracing.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Information complexity of stochastic convex optimization: Applications to generaliza- tion, memorization, and tracing

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.179459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d40188de-692a-4af9-b839-bce6d5f4da11 · outbound

This paper cites Does roberta perform better than bert in continual learning: An attention sink perspective.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Does roberta perform better than bert in continual learning: An attention sink perspective

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.184147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a43e384-f08c-4bd3-b7d2-8f1a5a6953fa · outbound

This paper cites Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.188363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0081a7f8-2acc-4de4-a885-da8b63eac5e7 · outbound

This paper cites Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.192997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc4952f-f1d4-4bfc-a3ac-39d1c456aa2f · outbound

This paper cites Network dissection: Quantifying inter- pretability of deep visual representations.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Network dissection: Quantifying inter- pretability of deep visual representations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.197280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672cbd99-3432-459d-9d08-e9753f17dec6 · outbound

This paper cites GAN Dissection: Visualizing and Understanding Generative Adversarial Networks.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.202035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b33995b7-9d20-4705-8d79-9976b506a789 · outbound

This paper cites The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.540224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6131caba-7c09-42ee-a2b8-42ecb92c94d4 · outbound

This paper cites Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.211478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9399ff0e-2079-4a67-959d-4b8119ecf00e · outbound

This paper cites Exploration by Random Network Distillation.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Exploration by Random Network Distillation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.215784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 114a3f33-5e2c-476a-85dc-deab160c6863 · outbound

This paper cites Adashift: Learning discriminative self-gated neural feature activation with an adaptive shift factor.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Adashift: Learning discriminative self-gated neural feature activation with an adaptive shift factor

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.219949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 214e7ad1-b916-4b6a-b7d9-afb943486e8e · outbound

This paper cites SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.224011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1404346b-e431-498d-9cf1-05439b9bf881 · outbound

This paper cites Dsg-kd: Knowledge distillation from domain-specific to general language models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Dsg-kd: Knowledge distillation from domain-specific to general language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.228291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2211fdf7-da9c-46e1-bfa4-1aaff186d18c · outbound

This paper cites Randaugment: Practical automated data augmen- tation with a reduced search space.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Randaugment: Practical automated data augmen- tation with a reduced search space

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.232148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876ac165-6165-43d3-b245-d0baa8faae10 · outbound

This paper cites Vision Transformers Need Registers.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Vision Transformers Need Registers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.235985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ec108e-aa52-4fa3-9256-3bee2df9b2da · outbound

This paper cites Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.240122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 640b3bb0-558c-4323-9259-af7ebb366ce3 · outbound

This paper cites Why fine-tuning strug- gles with forgetting in machine unlearning? theoretical in- sights and a remedial approach, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Why fine-tuning strug- gles with forgetting in machine unlearning? theoretical in- sights and a remedial approach, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.245327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ba789b3-e649-4170-a7f6-0a1075f88471 · outbound

This paper cites Decaf: A deep convolutional activation feature for generic visual recog- nition.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Decaf: A deep convolutional activation feature for generic visual recog- nition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.249103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b4e22b-710d-4091-a413-f1fa639e0274 · outbound

This paper cites Incorporating nesterov momentum into adam.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Incorporating nesterov momentum into adam

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.252823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a82ba2-91a9-4670-80f9-a7eb7839230a · outbound

This paper cites Rosetta neurons: Mining the common units in a model zoo.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Rosetta neurons: Mining the common units in a model zoo

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.256189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977e4b22-dbfc-4947-ac07-2454d47c1019 · outbound

This paper cites Compositional Generative Modeling: A Single Model is Not All You Need.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Compositional Generative Modeling: A Single Model is Not All You Need

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.260729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1017ebf1-703f-4d46-a7ca-d741c6be78b1 · outbound

This paper cites Content-adaptive non-local convolution for remote sensing pansharpening.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Content-adaptive non-local convolution for remote sensing pansharpening

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.264835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42489058-24f5-4dd1-9fbe-ae9611a3c9ad · outbound

This paper cites Roma: Robust dense feature matching.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Roma: Robust dense feature matching

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.268718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdbedd3-840e-4b97-b031-0e9d3fcea307 · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Scaling rectified flow transformers for high-resolution image synthesis

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.272493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6909d368-00b8-4182-ae49-e1862caf9052 · outbound

This paper cites KIF: Knowledge Identification and Fusion for Language Model Continual Learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections KIF: Knowledge Identification and Fusion for Language Model Continual Learning

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.459901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 84b8f97c-0045-4bcb-83bc-d07c15c3d2d4 · outbound

This paper cites Sharpness-aware minimization for efficiently improving generalization.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Sharpness-aware minimization for efficiently improving generalization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.281871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4205148-7bcf-4574-92ce-4cd166cb1d26 · outbound

This paper cites Enhancing elusive clues in knowledge learning by contrasting attention of language models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Enhancing elusive clues in knowledge learning by contrasting attention of language models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.444470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1fa23ffe-27bf-4d9e-87dc-2e07ef1b1a11 · outbound

This paper cites Building a Subspace of Policies for Scalable Continual Learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Building a Subspace of Policies for Scalable Continual Learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.290229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c538e3c6-04d4-4d8a-9823-7cd63c719167 · outbound

This paper cites What do Vision Transformers Learn? A Visual Exploration.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections What do Vision Transformers Learn? A Visual Exploration

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.294790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b56c4daf-f814-4e0d-93bf-81297f0dde9c · outbound

This paper cites Dropblock: A regularization method for convolutional networks.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Dropblock: A regularization method for convolutional networks

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.298957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a703ce3c-4b81-4869-9753-5d6f8495083c · outbound

This paper cites Task-adaptive pretrained language models via clustered- importance sampling, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Task-adaptive pretrained language models via clustered- importance sampling, 2024

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.302831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb8498f5-918a-464b-b78a-1b286b76ed4e · outbound

This paper cites Uncovering Unique Concept Vectors through Latent Space Decomposition.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Uncovering Unique Concept Vectors through Latent Space Decomposition

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.405019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 79cc3571-bd4d-4008-8dcd-f157ab9dcfec · outbound

This paper cites Preserving linear separability in continual learning by backward fea- ture projection.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Preserving linear separability in continual learning by backward fea- ture projection

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.311101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f7c1d7-ca2f-48cc-bd73-b09df54eb9ef · outbound

This paper cites Cpp-net: Embracing multi- scale feature fusion into deep unfolding cp-ppa network for compressive sensing.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Cpp-net: Embracing multi- scale feature fusion into deep unfolding cp-ppa network for compressive sensing

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.315029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfd57df-0f2a-40c5-84b0-6c70f5bba4e2 · outbound

This paper cites Slim: Let llm learn more and forget less with soft lora and identity mixture, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Slim: Let llm learn more and forget less with soft lora and identity mixture, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.318810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a1ebf6-8334-49ed-b550-b0e00a877f62 · outbound

This paper cites Upcycling large language models into mixture of experts, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Upcycling large language models into mixture of experts, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.323016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4e5943f-20ed-4030-9c47-660ae2cae5e8 · outbound

This paper cites Deep residual learning for image recognition.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Deep residual learning for image recognition

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.326778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f6b28c-ecc5-4799-8b2e-f750ca78d19a · outbound

This paper cites Identity mappings in deep residual networks.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Identity mappings in deep residual networks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.330840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a24bd6-254d-45ed-8572-62011876a6b1 · outbound

This paper cites Debiasing Text-to-Image Diffusion Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Debiasing Text-to-Image Diffusion Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.334833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f1685b-9721-42a7-b5e5-5ac80e22cdcc · outbound

This paper cites Bag of tricks for image classifica- tion with convolutional neural networks.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Bag of tricks for image classifica- tion with convolutional neural networks

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.338855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e19c15ab-fc8c-4246-ac2c-0202dd385d0e · outbound

This paper cites Gaussian Error Linear Units (GELUs).

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Gaussian Error Linear Units (GELUs)

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.343013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2059835e-b2da-4721-8deb-d2ec6a12e5a7 · outbound

This paper cites AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.347208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6b16bea-aca0-4275-aabf-eedcb00daa57 · outbound

This paper cites From Tinkering to Engineering: Measurements in Tensorflow Playground.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections From Tinkering to Engineering: Measurements in Tensorflow Playground

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.350773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0a966b85-62de-49a7-9723-e41f701799af · outbound

This paper cites Concept-centric transformers: Enhancing model inter- pretability through object-centric concept learning within a shared global workspace.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Concept-centric transformers: Enhancing model inter- pretability through object-centric concept learning within a shared global workspace

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.356522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6023e61a-039a-48f2-8c0e-4e68883d2d18 · outbound

This paper cites Deep networks with stochastic depth.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Deep networks with stochastic depth

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.360186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe44b1e7-18f2-4a2c-954a-40006be1113a · outbound

This paper cites Densely connected convolutional net- works.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Densely connected convolutional net- works

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.364021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672a06ae-1aa2-40fd-ade0-7ffdf494944b · outbound

This paper cites The Platonic Representation Hypothesis.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections The Platonic Representation Hypothesis

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.368244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 345110cd-1880-4ea9-bbbb-7bae5f24a974 · outbound

This paper cites Comparing the decision-making mechanisms by transformers and cnns via explanation methods.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Comparing the decision-making mechanisms by transformers and cnns via explanation methods

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.372556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42937489-2d40-45fb-8fdc-bc303b5286fa · outbound

This paper cites No train no gain: Revisiting ef- ficient training algorithms for transformer-based language models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections No train no gain: Revisiting ef- ficient training algorithms for transformer-based language models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.377230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80aa70c4-59cb-45a8-8793-5c7c72042506 · outbound

This paper cites Localized semantic feature mixers for effi- cient pedestrian detection in autonomous driving.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Localized semantic feature mixers for effi- cient pedestrian detection in autonomous driving

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.381557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fde43ec-adca-4ce4-9dc1-a7d900abe1ff · outbound

This paper cites SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Reference 52

Resolution: malformed identifier; no resolver link, observed 2026-08-12T20:40:32.385849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aef824f-4607-4852-a0b5-1e70087911a9 · outbound

This paper cites DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.309004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 144e9ef4-691c-4981-90de-42b5dc51cd3b · outbound

This paper cites Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.395287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4c6157-1879-426a-8dfe-0e51fc3b81db · outbound

This paper cites Feature separation and recalibration for adversarial robustness.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Feature separation and recalibration for adversarial robustness

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.399652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7077094f-4935-4e81-aeff-35fc09ffa50a · outbound

This paper cites Adam: A Method for Stochastic Optimization.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Adam: A Method for Stochastic Optimization

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.403541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c266adeb-e62f-4e31-bddf-bcacb2fff3ec · outbound

This paper cites Mean-shift feature transformer.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Mean-shift feature transformer

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.407809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f7a801-d199-49e3-89c0-5a937e3524e3 · outbound

This paper cites Learning multiple layers of features from tiny images.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Learning multiple layers of features from tiny images

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.411878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf77df9-f65a-4350-b2bf-9c10d50b00e4 · outbound

This paper cites Gradient-based learning applied to document recognition.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Gradient-based learning applied to document recognition

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.415892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a7fafad-f5fb-4fa7-b1c4-23d2ade44018 · outbound

This paper cites Fix the noise: Disen- tangling source feature for controllable domain translation.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Fix the noise: Disen- tangling source feature for controllable domain translation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.420043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb532026-debb-46ff-9005-98af1d30a79e · outbound

This paper cites Automated progres- sive learning for efficient training of vision transformers.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Automated progres- sive learning for efficient training of vision transformers

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.424030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74bf4e8f-8b9b-4268-abf2-361f2f37ba37 · outbound

This paper cites Robustness preserving fine-tuning using neuron importance.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Robustness preserving fine-tuning using neuron importance

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.427796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd9a0878-4cdc-47ff-9b67-7b68b3ea07f8 · outbound

This paper cites Formality is favored: Unraveling the learning preferences of large language models on data with conflicting knowl- edge, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Formality is favored: Unraveling the learning preferences of large language models on data with conflicting knowl- edge, 2024

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.431352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6956a347-ffc5-4625-8a00-3545ff4219dc · outbound

This paper cites Adver- sarial feature hallucination networks for few-shot learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Adver- sarial feature hallucination networks for few-shot learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.434966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1763176-a908-4b89-9cb7-8133c149bee9 · outbound

This paper cites Parameter-efficient fine- tuning in spectral domain for point cloud learning, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Parameter-efficient fine- tuning in spectral domain for point cloud learning, 2024

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.438512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e0d7be1-3423-4b62-b00c-c609ae894960 · outbound

This paper cites Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.442547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259464c2-58aa-470a-84b3-811f52229890 · outbound

This paper cites Class Incremental Learning via Likelihood Ratio Based Task Prediction.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Class Incremental Learning via Likelihood Ratio Based Task Prediction

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.446984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57142313-9e41-477b-857e-834e6af16eaf · outbound

This paper cites Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.261782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 92a00115-a0b8-41d6-ae0a-9978ddee6a25 · outbound

This paper cites Soft augmentation for image classification.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Soft augmentation for image classification

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.455335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08aafce-40c6-4850-94d3-79a71a7e938b · outbound

This paper cites PAT: Pruning-Aware Tuning for Large Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections PAT: Pruning-Aware Tuning for Large Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.459906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf18578-27e6-4d7c-a720-e44f3322109b · outbound

This paper cites UNLEARN Efficient Removal of Knowledge in Large Language Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections UNLEARN Efficient Removal of Knowledge in Large Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.464254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b289fb-5e52-4add-b026-acba3cf976c4 · outbound

This paper cites Decoupled Weight Decay Regularization.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Decoupled Weight Decay Regularization

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.468168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce497222-1214-4abd-84cd-b0372908f54d · outbound

This paper cites Mono-internvl: Pushing the boundaries of monolithic multimodal large language mod- els with endogenous visual pre-training, 2024.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Mono-internvl: Pushing the boundaries of monolithic multimodal large language mod- els with endogenous visual pre-training, 2024

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.472102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1875d522-073c-4895-9403-dce6fa641eb1 · outbound

This paper cites Language Models "Grok" to Copy.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Language Models "Grok" to Copy

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.476689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 625ccbee-7c5b-466f-8ada-497fb5d72e50 · outbound

This paper cites Curvature-balanced feature manifold learning for long-tailed classification.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Curvature-balanced feature manifold learning for long-tailed classification

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.480740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a98b2e-8671-435b-a1a1-4deda0e11923 · outbound

This paper cites Finite Scalar Quantization: VQ-VAE Made Simple.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Finite Scalar Quantization: VQ-VAE Made Simple

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.484550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd91c859-0a32-4d3c-911f-00d179f95460 · outbound

This paper cites Pace: marrying generalization in parameter-efficient fine-tuning with con- sistency regularization.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Pace: marrying generalization in parameter-efficient fine-tuning with con- sistency regularization

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.488915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68e32e63-0da0-452f-b9ee-8003a0c8a7d1 · outbound

This paper cites House of Cards: Massive Weights in LLMs.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections House of Cards: Massive Weights in LLMs

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.492952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc6dfe18-9b7a-497e-b196-515519821620 · outbound

This paper cites Zoom in: An in- troduction to circuits.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Zoom in: An in- troduction to circuits

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.497003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69ce8d33-93e5-46c7-970a-48a510dfa587 · outbound

This paper cites an unresolved cited work.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Unresolved cited work

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.501081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17e80e0-446a-4c37-be1f-8d4c64213db9 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections DINOv2: Learning Robust Visual Features without Supervision

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.505125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91eb28c6-cb86-4b0a-8550-4af381a55edc · outbound

This paper cites Diverse Feature Learning by Self-distillation and Reset.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Diverse Feature Learning by Self-distillation and Reset

Reference 82

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:33.104055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 33a98791-f255-49a7-854b-a8fa29a4fd53 · outbound

This paper cites Learning More Generalized Experts by Merging Experts in Mixture-of-Experts.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Learning More Generalized Experts by Merging Experts in Mixture-of-Experts

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.513218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e216f7-2ddb-4233-9dc7-0c728a4b8941 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.517642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d9cadc-cd00-4cfa-9b0b-90d89d4069bd · outbound

This paper cites Enhancing deformable local features by jointly learning to detect and describe keypoints.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Enhancing deformable local features by jointly learning to detect and describe keypoints

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.521476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6572b150-c6cd-4eb5-8cd7-7f4a59a616f3 · outbound

This paper cites Cafeboost: Causal feature boost to eliminate task-induced bias for class incremental learning.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Cafeboost: Causal feature boost to eliminate task-induced bias for class incremental learning

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.525110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f905da-9efb-437a-82d8-af92c793e604 · outbound

This paper cites Unlocking emergent modularity in large language models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Unlocking emergent modularity in large language models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.528820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb570f63-1bf4-40f2-bcec-e88b435db7aa · outbound

This paper cites Berg, and Li Fei-Fei.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Berg, and Li Fei-Fei

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.532215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36338cff-0af2-4f35-92b2-ff68efbcd535 · outbound

This paper cites LARE: Latent Augmentation using Regional Embedding with Vision-Language Model.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections LARE: Latent Augmentation using Regional Embedding with Vision-Language Model

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.535730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 360b389d-40b6-447f-a2ff-76778bcc1e9a · outbound

This paper cites Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.540034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea7b32cf-bcf0-4e96-b727-86f5606cfe25 · outbound

This paper cites Overcoming catastrophic forgetting with hard attention to the task.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Overcoming catastrophic forgetting with hard attention to the task

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.544274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4914e393-4859-4010-b77e-cfc1f17ee81c · outbound

This paper cites Adaptive subspaces for few-shot learn- ing.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Adaptive subspaces for few-shot learn- ing

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:40:33.838632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6086a63b-06a1-4ccc-adc5-6760b257f678 · outbound

This paper cites SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.551847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e09cc5-fc8d-4cd6-a81b-74fe98a295ed · outbound

This paper cites Out-of-distribution generalization via composition: a lens through induction heads in Transformers.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Out-of-distribution generalization via composition: a lens through induction heads in Transformers

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.556025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab5d4894-bf8d-4708-b67f-6c192d26b423 · outbound

This paper cites Striving for Simplicity: The All Convolutional Net.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Striving for Simplicity: The All Convolutional Net

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.560955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece05c83-4f0e-44d9-963d-0b3fbe2ff165 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Dropout: a simple way to prevent neural networks from overfitting

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:40:33.826548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 845787ec-fb17-4aa5-8daa-d80df77fef45 · outbound

This paper cites Locat- ing information in large language models via random ma- trix theory.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Locat- ing information in large language models via random ma- trix theory

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.568905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1477b1-6c72-4774-8258-d9ab2dd22683 · outbound

This paper cites SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values

Reference 98

Resolution: verified exact; local_arxiv, observed 2026-08-12T20:40:32.953829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1a2045b4-8bbc-41ec-ab96-8e3cbe3613fd · outbound

This paper cites SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-12T20:40:32.576545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53277d80-a6c4-479f-bef9-9e9f9ac136da · outbound

This paper cites Scaling monosemanticity: Extracting in- terpretable features from claude 3 sonnet.

ResidualDroppath: Enhancing Feature Reuse over Residual Connections Scaling monosemanticity: Extracting in- terpretable features from claude 3 sonnet

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T20:40:33.815169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers