oceansweep (r)

upvoted a paper about 21 hours ago

Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study

Paper • 2409.17580 • Published 3 days ago • 4

upvoted a paper 2 days ago

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published 3 days ago • 69

upvoted 2 papers 3 days ago

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling

Paper • 2409.16160 • Published 4 days ago • 27

HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models

Paper • 2409.16191 • Published 4 days ago • 36

upvoted a collection 3 days ago

Molmo

Collection

Artifacts for open multimodal language models. • 5 items • Updated 3 days ago • 179

upvoted an article 4 days ago

Article

Does Daily Software Engineering Work Need Reasoning Models?

By

•

5 days ago

• 4

upvoted a paper 5 days ago

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation

Paper • 2409.12941 • Published 9 days ago • 13

upvoted 4 papers 9 days ago

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Paper • 2409.10173 • Published 13 days ago • 20

Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models

Paper • 2409.12139 • Published 10 days ago • 11

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Paper • 2409.12183 • Published 10 days ago • 30

A Controlled Study on Long Context Extension and Generalization in LLMs

Paper • 2409.12181 • Published 10 days ago • 40

upvoted a paper 10 days ago

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published 11 days ago • 4

upvoted a collection 11 days ago

MagpieLM

Collection

Aligning LMs with Fully Open Recipe (data+training configs+logs) • 9 items • Updated 6 days ago • 13

upvoted a paper 16 days ago

PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation

Paper • 2409.06820 • Published 18 days ago • 57

upvoted a paper 17 days ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published 26 days ago • 75

upvoted 2 papers 23 days ago

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Paper • 2409.02897 • Published 24 days ago • 43

ContextCite: Attributing Model Generation to Context

Paper • 2409.00729 • Published 27 days ago • 13

upvoted a paper 26 days ago

SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section

Paper • 2408.16444 • Published about 1 month ago • 8

upvoted 2 papers about 1 month ago

Sapiens: Foundation for Human Vision Models

Paper • 2408.12569 • Published Aug 22 • 86

LLaVaOLMoBitnet1B: Ternary LLM goes Multimodal!

Paper • 2408.13402 • Published Aug 23 • 17

upvoted a collection about 1 month ago

CogVideo

Collection

7 items • Updated 10 days ago • 18

upvoted 7 papers about 1 month ago

FocusLLM: Scaling LLM's Context by Parallel Decoding

Paper • 2408.11745 • Published Aug 21 • 23

LLM Pruning and Distillation in Practice: The Minitron Approach

Paper • 2408.11796 • Published Aug 21 • 53

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Paper • 2408.08152 • Published Aug 15 • 51

Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability

Paper • 2408.07852 • Published Aug 14 • 14

The ShareLM Collection and Plugin: Contributing Human-Model Chats for the Benefit of the Community

Paper • 2408.08291 • Published Aug 15 • 9

Imagen 3

Paper • 2408.07009 • Published Aug 13 • 60

MovieSum: An Abstractive Summarization Dataset for Movie Screenplays

Paper • 2408.06281 • Published Aug 12 • 9

upvoted a collection about 2 months ago

InternLM2.5

Collection

14 items • Updated 14 days ago • 67

upvoted 12 papers about 2 months ago

LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models

Paper • 2406.00605 • Published Jun 2 • 2

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs

Paper • 2407.02485 • Published Jul 2 • 5

Characterizing Prompt Compression Methods for Long Context Inference

Paper • 2407.08892 • Published Jul 11 • 9

Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs

Paper • 2406.02376 • Published Jun 4 • 1

IAPT: Instruction-Aware Prompt Tuning for Large Language Models

Paper • 2405.18203 • Published May 28 • 1

SelfCP: Compressing Long Prompt to 1/12 Using the Frozen Large Language Model Itself

Paper • 2405.17052 • Published May 27 • 1

LoCoCo: Dropping In Convolutions for Long Context Compression

Paper • 2406.05317 • Published Jun 8 • 1

Recurrent Context Compression: Efficiently Expanding the Context Window of LLM

Paper • 2406.06110 • Published Jun 10 • 1

Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities

Paper • 2406.11357 • Published Jun 17 • 1

Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation

Paper • 2408.00205 • Published Aug 1 • 4

MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains

Paper • 2407.18961 • Published Jul 18 • 38

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

Paper • 2406.10149 • Published Jun 14 • 48

upvoted 2 papers 2 months ago

Compact Language Models via Pruning and Knowledge Distillation

Paper • 2407.14679 • Published Jul 19 • 35

VideoGameBunny: Towards vision assistants for video games

Paper • 2407.15295 • Published Jul 21 • 21

upvoted a collection 2 months ago

AQLM

Collection

AQLM quantized LLMs • 20 items • Updated May 3 • 42

upvoted 4 papers 2 months ago

upvoted 2 articles 2 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 329

Article

BigCodeBench: Benchmarking Large Language Models on Solving Practical and Challenging Programming Tasks

Jun 18

• 35

upvoted 2 papers 2 months ago

LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Paper • 2407.12772 • Published Jul 17 • 33

Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models

Paper • 2407.12327 • Published Jul 17 • 75

upvoted a collection 2 months ago

TriLMs-Unpacked

Collection

TriLMs unpacked to FP16 - compatible with any implementation supporting LLaMa architecture in huggingface's transformers format. • 9 items • Updated Jul 9 • 4

upvoted 7 papers 3 months ago

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Paper • 2407.07071 • Published Jul 9 • 11

Direct Preference Knowledge Distillation for Large Language Models

Paper • 2406.19774 • Published Jun 28 • 21

LiteSearch: Efficacious Tree Search for LLM

Paper • 2407.00320 • Published Jun 29 • 37

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

Paper • 2407.01920 • Published Jul 2 • 13

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1 • 42

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Paper • 2407.01370 • Published Jul 1 • 84

Can LLMs Learn by Teaching? A Preliminary Study

Paper • 2406.14629 • Published Jun 20 • 17

r PRO

AI & ML interests

Organizations

oceansweep's activity

Does Daily Software Engineering Work Need Reasoning Models?

Uncensor any LLM with abliteration

BigCodeBench: Benchmarking Large Language Models on Solving Practical and Challenging Programming Tasks