PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts | Paper Citation Record

Observation 7eea74f6-9ee1-4216-9e36-571f6d6a40cb · outbound

This paper cites SemDeDup: Data-efficient learning at web-scale through semantic deduplication.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts SemDeDup: Data-efficient learning at web-scale through semantic deduplication

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:37.957601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5bc95b-0130-44d0-921e-ae70424bf682 · outbound

This paper cites Layer Normalization.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Layer Normalization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.007383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d16e5144-f9a8-4058-bfa5-f7d3dd021705 · outbound

This paper cites Fair Resource Allocation in Multi-Task Learning.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Fair Resource Allocation in Multi-Task Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.048244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab05056-708a-4eb4-b699-1bfbf031ea6a · outbound

This paper cites Bengio, J.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Bengio, J

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.647558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fed561dd-2124-4d5c-af46-cfe9dd3142c6 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.631923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2e23761e-4bfd-4014-94fd-3a07a21c1811 · outbound

This paper cites Bradbury, R.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Bradbury, R

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.616164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aa8495b0-9022-44dc-becb-07962b10f208 · outbound

This paper cites Brown, B.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Brown, B

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.146418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4022e036-0f92-4b20-8b65-d5ef5535eb82 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.591008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e24d4ab6-2d26-45b4-8e5a-8ea07cd90dcc · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts PaLM: Scaling Language Modeling with Pathways

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.154722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d509d39f-d615-4941-ac6b-5fcd5d29086f · outbound

This paper cites Chowdhery, S.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Chowdhery, S

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.159387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80aa0092-58bc-4014-88ef-842146fc39e6 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.163261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d68fc0-18d1-4ceb-acfb-3d044c95a3e5 · outbound

This paper cites Dac Lai, C.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Dac Lai, C

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.565564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96c48b7a-c554-44f2-a567-4220d5598043 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.550380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9573a299-a857-4fa5-b700-90716e570d7b · outbound

This paper cites Scaling Vision Transformers to 22 Billion Parameters.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Scaling Vision Transformers to 22 Billion Parameters

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.174869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 222aa175-a7e4-4552-b185-e831da369416 · outbound

This paper cites Désidéri.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Désidéri

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.535036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6438c6fd-f81f-4cc1-8d9f-eb804d00af1e · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.183058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d59d02a-9f09-4bd5-93ca-04f7984c889f · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.519550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 51faab7c-590c-49ee-bbde-47358fd8bc07 · outbound

This paper cites The Llama 3 Herd of Models.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.191917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3b51c1-4a66-43af-8dc0-93f942f09b8d · outbound

This paper cites Gaffney, D.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Gaffney, D

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.503601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ae15711a-4fc0-4c9e-b3f8-47b28790e8a6 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.201229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f39b70b-f8fe-45e9-9077-f493172e22b9 · outbound

This paper cites Metadata Conditioning Accelerates Language Model Pre-training.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Metadata Conditioning Accelerates Language Model Pre-training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.205938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1e18744-1e5a-4135-a13b-a28118e13e12 · outbound

This paper cites BiMix: A Bivariate Data Mixing Law for Language Model Pretraining.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts BiMix: A Bivariate Data Mixing Law for Language Model Pretraining

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.210654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa4398d-d4b3-4e59-9229-df950679d7bc · outbound

This paper cites Grain - feeding jax models, 2023.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Grain - feeding jax models, 2023

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.486669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ec5e14aa-2d17-4068-8c94-99f3c1b3ecea · outbound

This paper cites OLMES: A Standard for Language Model Evaluations.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts OLMES: A Standard for Language Model Evaluations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.219629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49da94a5-ba5d-4592-9fc8-99793e945086 · outbound

This paper cites Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.223631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9704e15c-f232-4f7a-9ab6-02d7f1c73330 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.471360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e3362410-cd3a-4c67-9954-9a3cba00c1cc · outbound

This paper cites Hoffmann, S.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Hoffmann, S

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.456007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c682751e-f173-4956-b12a-2c77e6c2917b · outbound

This paper cites Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.235917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f930fb-f5ef-4ab3-a575-c6000b0a0f97 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.440017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5e6ab6f4-8e25-47d9-8bf6-b33023df33df · outbound

This paper cites Laurençon, L.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Laurençon, L

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.424986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 99ab4cc0-eb81-487a-b8c9-a410b53ec1d9 · outbound

This paper cites Deduplicating Training Data Makes Language Models Better.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Deduplicating Training Data Makes Language Models Better

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.248064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df1ed79-cb88-45ba-b876-2abb3c65208e · outbound

This paper cites Measuring the Intrinsic Dimension of Objective Landscapes.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Measuring the Intrinsic Dimension of Objective Landscapes

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.252309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7165800-d266-43e5-a708-d1d9beb882d8 · outbound

This paper cites Tilted Empirical Risk Minimization.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Tilted Empirical Risk Minimization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.256693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ebbc5bc-b4bd-4e9f-b7c8-538b129b2a3b · outbound

This paper cites DeepSeek-V3 Technical Report.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts DeepSeek-V3 Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.261204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75570df8-02cd-49dc-99e2-82ef62db82c9 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.265770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 987a94fa-0333-4995-acd7-d7687431f4c6 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.399591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c7e739be-ec96-4b2c-b030-bbec1ed76556 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.384081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c446b3ae-c66f-4750-a6fa-c89a146a83e0 · outbound

This paper cites RegMix: Data Mixture as Regression for Language Model Pre-training.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts RegMix: Data Mixture as Regression for Language Model Pre-training

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.278606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf503f5f-4eb8-4b62-b3c9-9199d29ad02d · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.368238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0f5ff7bc-e362-4451-ad1d-a7f9cf62e3c7 · outbound

This paper cites Multi-Task Deep Neural Networks for Natural Language Understanding.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Multi-Task Deep Neural Networks for Natural Language Understanding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.287083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ccfab3-0751-4d21-a7a3-10c1c037aedd · outbound

This paper cites Loshchilov and F.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Loshchilov and F

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.351350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cf99c504-1c9a-432f-8198-869faa32fc2a · outbound

This paper cites Multi-task Sequence to Sequence Learning.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Multi-task Sequence to Sequence Learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.295637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1afe68c2-849a-4d38-a71f-28fa749b8153 · outbound

This paper cites Misra, A.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Misra, A

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.335747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8e41af2d-9a11-4b02-8e50-03665eada8c5 · outbound

This paper cites Mo and J.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Mo and J

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.319555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a1e5879-c521-45b6-917c-5dbe6f8d4c9c · outbound

This paper cites Multi-Task Learning as a Bargaining Game.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Multi-Task Learning as a Bargaining Game

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.309736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a4ba645-45b0-4ec2-b908-470ef9279f98 · outbound

This paper cites Penedo, Q.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Penedo, Q

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.303950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e1d548c3-28ac-4e0a-95d0-46a1553ef4b7 · outbound

This paper cites Radford, J.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Radford, J

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.288553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2ef21911-e49e-48be-ab7c-68bfb4258a3c · outbound

This paper cites Scaling Language Models: Methods, Analysis & Insights from Training Gopher.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Scaling Language Models: Methods, Analysis & Insights from Training Gopher

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.323545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b76872-62a3-40d7-a582-b15917294a48 · outbound

This paper cites Raffel, N.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Raffel, N

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.328289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7f54b89-7261-465a-9cf9-503e944282ab · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.261658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fdc47634-9848-43c4-abfd-35cbbe314686 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.246529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d8736690-d5ea-4809-bf17-54a48c7eb8bd · outbound

This paper cites Ruder, J.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Ruder, J

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.230987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1d43c75f-11a3-48e7-8928-a35bf4795c4b · outbound

This paper cites How to Train Data-Efficient LLMs.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts How to Train Data-Efficient LLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.347017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403571f5-d54f-47b8-9a38-be03c2d9339b · outbound

This paper cites Sener and V.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Sener and V

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.216383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c2be998-8b9a-4f80-a280-c8c336a5c1bf · outbound

This paper cites Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.356201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9be65c8-ad75-433f-8db5-5058dfd3ef87 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.360914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d9457b-b5c7-4ec6-a3b4-61239f420115 · outbound

This paper cites CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.365866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22ca0db-c68d-4623-9a52-b12d456b3865 · outbound

This paper cites Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.370936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88a8da9a-7b5c-41d3-9d59-266cfc7d4f69 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Gemini: A Family of Highly Capable Multimodal Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.375675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447e7f22-6ef8-4866-8fa7-81b1eeffe5ff · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.380223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1334642-6086-463b-9e70-0259f235dc81 · outbound

This paper cites Vandenhende, S.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Vandenhende, S

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T16:20:39.200772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7fcbe20f-713a-4f59-aad5-012ad183fe53 · outbound

This paper cites Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.389831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86bf22b8-0dc6-4043-a6f1-8ff7c8787b75 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.394565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b60273fd-11f9-4a60-a61d-f52a6d896b45 · outbound

This paper cites Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.399019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55dfd1c6-7e30-49b7-ace6-f1c89c901824 · outbound

This paper cites QuRating: Selecting High-Quality Data for Training Language Models.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts QuRating: Selecting High-Quality Data for Training Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.403659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2010af6c-5a83-440d-8144-4115041fd377 · outbound

This paper cites Small-scale proxies for large-scale Transformer training instabilities.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Small-scale proxies for large-scale Transformer training instabilities

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.408373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b18f82e8-ea7b-42dd-b668-4d9ab07d267d · outbound

This paper cites Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.413011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12476dd6-b919-42df-a259-77720843e885 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.174015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3bc8e8d-d6b4-4994-a9f0-578e3199c325 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.158872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0bd3df9e-7d8b-44d7-a9ca-df8be45cc50c · outbound

This paper cites mT5: A massively multilingual pre-trained text-to-text transformer.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts mT5: A massively multilingual pre-trained text-to-text transformer

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.426348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1b2ca3-f15d-432c-b82b-4d3bc560187b · outbound

This paper cites ByT5: Towards a token-free future with pre-trained byte-to-byte models.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts ByT5: Towards a token-free future with pre-trained byte-to-byte models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.430971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdeffc12-87f1-4fb0-a7dd-6b16b2c8bc86 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.142824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6573b0bb-16db-45b0-b561-b91f1d432115 · outbound

This paper cites Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.440209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03962849-f2b2-4453-bb7e-f8d3426bd3a9 · outbound

This paper cites an unresolved cited work.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-08T16:20:39.126374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39479523-eb42-40a3-8967-a13e0f4595a5 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.449710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faaeb223-ad35-4ee3-baf9-813f5dbef9fe · outbound

This paper cites Why Transformers Need Adam: A Hessian Perspective.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts Why Transformers Need Adam: A Hessian Perspective

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-08T16:20:38.454661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 689bb806-2dd1-40a5-b6c1-2b897d0383f1 · outbound

This paper cites ratio,” which defined as ⟨Lj (θ),Lk(θ)⟩ ∥Lj (θ)∥2+∥Lk(θ)∥2 , between task gradients during language model pre-training over time. “ data1- data2.

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts ratio,” which defined as ⟨Lj (θ),Lk(θ)⟩ ∥Lj (θ)∥2+∥Lk(θ)∥2 , between task gradients during language model pre-training over time. “ data1- data2

Reference 77

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T16:20:39.109219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers