AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
hub Mixed citations
Lora: Low-rank adaptation of large language models.Iclr, 1(2):3
Mixed citation behavior. Most common role is method (60%).
50
Pith papers citing it
Method
60% of classified citations
hub tools
citation-role summary
method 9
background 4
baseline 2
citation-polarity summary
years
2026 50representative citing papers
CDM migrates distribution matching distillation to continuous time via dynamic random-length schedules and active off-trajectory latent alignment, yielding competitive few-step image fidelity on SD3 and Longcat-Image.
OvESyn is the first text-conditioned 3D CT synthesis framework for abdomino-pelvic oncologic imaging, constructing evidence-based text from metadata to adapt a latent diffusion model across the domain gap from chest CT pretraining.
MADField is a multi-fidelity amortized model for predicting density fields to improve accuracy and speed of adsorption calculations in nanoporous materials for high-throughput screening.
Self-Policy Distillation extracts a capability subspace from model gradients on correctness tokens, projects KV activations into it for self-generation, and fine-tunes LLMs to achieve up to 13-16% gains over baselines without external signals.
LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.
Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
WEBSHORTS dataset and SHORTS-CAST framework ground micro-video popularity prediction in structured open-web context collected at upload time and enable selective online adaptation using delayed labels.
Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
DRAPE generates query-image conditioned prompts on the fly for multimodal continual instruction tuning and reports SOTA results on MCIT benchmarks.
TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temporal tasks.
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
Fine-tuning a video generator on a new 17K reasoning-video dataset improves Chain-of-Frame reasoning, and adding learnable visual/textual reasoning tokens yields further gains on external benchmarks.
Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
Joint AR–diffusion training yields one tri-mode LM that switches AR, diffusion, and self-speculation, beating open AR/diffusion models on accuracy and tokens-per-forward.
PALoRA identifies reasoning-critical singular subspaces via SVF and constrains subsequent LoRA updates to be orthogonal to them, preserving 95% of reasoning performance on average across tested models and benchmarks.
ChunkFT enables full-parameter fine-tuning of Llama 3-8B on one 24 GB GPU and Llama 3-70B on two 80 GB GPUs by streaming gradients over dynamically activated sub-tensors.
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
CPC-VAR adds Gradient-based Concept Neuron Selection for continual single-concept learning and a context-aware multi-branch composition strategy to reduce forgetting and entanglement in VAR-based personalized image generation.
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.
BTECF encodes retinal vessels as Bézier trees to enable targeted, parameter-level counterfactual interventions on vessel geometry for causal analysis of vascular diseases.
citing papers explorer
-
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.
-
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
CDM migrates distribution matching distillation to continuous time via dynamic random-length schedules and active off-trajectory latent alignment, yielding competitive few-step image fidelity on SD3 and Longcat-Image.
-
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
OvESyn is the first text-conditioned 3D CT synthesis framework for abdomino-pelvic oncologic imaging, constructing evidence-based text from metadata to adapt a latent diffusion model across the domain gap from chest CT pretraining.
-
MADField: Multi-fidelity Amortized Density Field for Adsorption in Nanoporous Materials
MADField is a multi-fidelity amortized model for predicting density fields to improve accuracy and speed of adsorption calculations in nanoporous materials for high-throughput screening.
-
Self-Policy Distillation via Capability-Selective Subspace Projection
Self-Policy Distillation extracts a capability subspace from model gradients on correctness tokens, projects KV activations into it for self-generation, and fine-tunes LLMs to achieve up to 13-16% gains over baselines without external signals.
-
LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue
LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.
-
Aurora: Unified Video Editing with a Tool-Using Agent
Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
-
Will It Go Viral? Grounding Micro-Video Popularity Prediction on the Open Web
WEBSHORTS dataset and SHORTS-CAST framework ground micro-video popularity prediction in structured open-web context collected at upload time and enable selective online adaptation using delayed labels.
-
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
Fine-tuning neural PDE operators to regime endpoints reveals a physical direction in weight space that CCM uses to compose accurate merged models for new or extrapolated regimes from metadata or short prefixes.
-
Query-Conditioned Test-Time Self-Training for Large Language Models
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
-
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
DRAPE generates query-image conditioned prompts on the fly for multimodal continual instruction tuning and reports SOTA results on MCIT benchmarks.
-
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
-
Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs
Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temporal tasks.
-
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
-
OpenCoF: Learning to Reason Through Video Generation
Fine-tuning a video generator on a new 17K reasoning-video dataset improves Chain-of-Frame reasoning, and adding learnable visual/textual reasoning tokens yields further gains on external benchmarks.
-
When Does Continual Learning Require Learning
Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
-
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
Joint AR–diffusion training yields one tri-mode LM that switches AR, diffusion, and self-speculation, beating open AR/diffusion models on accuracy and tokens-per-forward.
-
PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models
PALoRA identifies reasoning-critical singular subspaces via SVF and constrains subsequent LoRA updates to be orthogonal to them, preserving 95% of reasoning performance on average across tested models and benchmarks.
-
ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
ChunkFT enables full-parameter fine-tuning of Llama 3-8B on one 24 GB GPU and Llama 3-70B on two 80 GB GPUs by streaming gradients over dynamically activated sub-tensors.
-
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
-
CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models
CPC-VAR adds Gradient-based Concept Neuron Selection for continual single-concept learning and a context-aware multi-branch composition strategy to reduce forgetting and entanglement in VAR-based personalized image generation.
-
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
-
Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.
-
A General B\'ezier Tree Encoding Counterfactual Framework for Retinal-Vessel-Mediated Disease Analysis
BTECF encodes retinal vessels as Bézier trees to enable targeted, parameter-level counterfactual interventions on vessel geometry for causal analysis of vascular diseases.
-
In-context learning to predict critical transitions in dynamical systems
TipPFN uses prior-data fitted networks and in-context learning on synthetic bifurcation data to detect proximity to critical transitions in unseen dynamical systems and real observations.
-
G-Zero: Self-Play for Open-Ended Generation from Zero Data
G-Zero uses the Hint-δ intrinsic reward to drive co-evolution between a Proposer and Generator via GRPO and DPO, providing a theoretical suboptimality guarantee for self-improvement from internal dynamics alone.
-
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
Learns state-conditioned commitment depth in a 7B vision-language policy that jointly predicts actions and replan intervals, outperforming fixed-depth baselines and larger models on Sliding Puzzle and Sokoban while providing a theoretical dominance result.
-
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Muon-OGD introduces a spectral-norm constrained orthogonal projection method solved via dual iterations and Newton-Schulz approximations to improve stability-plasticity trade-off in sequential LLM adaptation.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
-
From History to State: Constant-Context Skill Learning for LLM Agents
Constant-context skill learning trains reusable task-family modules for LLM agents using a deterministic state block for progress tracking and subgoal rewards, achieving 89.6% unseen success on ALFWorld, 76.8% on WebShop, and 66.4% on SciWorld with Qwen3-8B while reducing prompt tokens 2-7x.
-
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.
-
Towards Lawful Autonomous Driving: Deriving Scenario-Aware Driving Requirements from Traffic Laws and Regulations
Grounding LLMs via node-wise anchors in a traffic scenario taxonomy improves law-scenario matching by 29.1% and derived requirement accuracy by 36.9-38.2% on Chinese laws and 5,897 scenarios, enabling a compliance layer and real-time monitor for AVs.
-
Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation
DALorRA applies variational Bayesian sparse masking to LoRA ranks to calibrate LLM uncertainty while preserving accuracy.
-
Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
A state distribution view of post-training shows that on-policy supervision from the learner itself can outperform fixed-dataset SFT and preserve retention better than aggressive supervised updates.
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
FINCH is a loss-adaptive learning-rate schedule that reduces forgetting by 93% on average during LLM fine-tuning while matching standard task performance across several benchmarks.
-
Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
SFT on LLMs removes noise-like token interactions in a brief early phase before introducing overfitted ones, explaining inconsistent effectiveness across model scales.
-
Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
Omni-Customizer proposes an end-to-end framework using Omni-Context Fusion, Masked TTS Cross-Attention, Semantic-Anchored Multimodal RoPE, and specialized training curricula to achieve precise multimodal identity binding in joint audio-video generation.
-
HDRFace: Rethinking Face Restoration with High-Dimensional Representation
HDRFace injects high-dimensional facial features from low-quality and intermediate images into diffusion models via SDFM fusion, reporting gains on SD V2.1-base and Qwen-Image.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
-
bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
A 12-step single-block recurrent ViT-B reaches accuracy comparable to a standard ViT-B on ImageNet-1K while using an order of magnitude fewer parameters.
-
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
LiteMedCoT-VL distills chain-of-thought from a 235B model to 2B VLMs via LoRA, reaching 64.9% accuracy on PMC-VQA and beating a 4B zero-shot baseline by 11 points.
-
Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
SPEAR enables online federated LLM fine-tuning by using feedback-guided self-play to create contrastive pairs trained with maximum likelihood on correct completions and confidence-weighted unlikelihood on incorrect ones, outperforming baselines without ground-truth contexts.
-
Attribution-Guided Continual Learning for Large Language Models
LRP-derived element-wise parameter importance scores gate gradients so parameters critical to earlier tasks receive smaller updates during continual LLM fine-tuning.
-
Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
LoPT splits LLM post-training at the midpoint with task loss on the second half and feature reconstruction on the first half to reduce cost and interference.
-
Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning
A framework with similarity-based visual token compression, dynamic attention rebalancing, and explicit inductive-deductive chain-of-thought improves multimodal ICL performance across eight benchmarks for open-source VLMs.
-
HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.
-
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
Diffusion Templates is a unified plugin framework that allows injecting various controllable capabilities into diffusion models through a standardized interface.
-
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
HARNESS-LM uses teacher fine-tuning, L2 query alignment, and contrastive refinement to distill large SLM retrievers into compact models that recover 98% precision with up to 27x lower latency on Bing Ads benchmarks.
-
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
A literature survey that unifies fragmented work on attacks, defenses, evaluations, and deployment challenges for Vision-Language-Action models in robotics.
- $x$-Prediction Flow: Efficient Continuous Decoding for Masked Diffusion Language Models