Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
Paper
•
2403.09029
•
Published
•
55
cool-papers
-
-
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Paper • 2403.12968 • Published • 25 -
RAFT: Adapting Language Model to Domain Specific RAG
Paper • 2403.10131 • Published • 72 -
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Paper • 2403.09629 • Published • 78 -
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Paper • 2403.08763 • Published • 51 -
Language models scale reliably with over-training and on downstream tasks
Paper • 2403.08540 • Published • 15 -
Algorithmic progress in language models
Paper • 2403.05812 • Published • 20 -
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Paper • 2403.05530 • Published • 66 -
TnT-LLM: Text Mining at Scale with Large Language Models
Paper • 2403.12173 • Published • 20 -
Larimar: Large Language Models with Episodic Memory Control
Paper • 2403.11901 • Published • 33 -
Reverse Training to Nurse the Reversal Curse
Paper • 2403.13799 • Published • 13 -
When Do We Not Need Larger Vision Models?
Paper • 2403.13043 • Published • 26 -
MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?
Paper • 2403.14624 • Published • 53 -
FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
Paper • 2403.15246 • Published • 11 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 33 -
The Unreasonable Ineffectiveness of the Deeper Layers
Paper • 2403.17887 • Published • 82 -
Long-form factuality in large language models
Paper • 2403.18802 • Published • 26 -
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Paper • 2403.18421 • Published • 23 -
Octopus v2: On-device language model for super agent
Paper • 2404.01744 • Published • 58 -
Poro 34B and the Blessing of Multilinguality
Paper • 2404.01856 • Published • 15 -
Long-context LLMs Struggle with Long In-context Learning
Paper • 2404.02060 • Published • 37 -
Training LLMs over Neurally Compressed Text
Paper • 2404.03626 • Published • 24 -
CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
Paper • 2404.03543 • Published • 18 -
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
Paper • 2404.02575 • Published • 50 -
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Paper • 2404.12253 • Published • 55 -
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 28 -
Flamingo: a Visual Language Model for Few-Shot Learning
Paper • 2204.14198 • Published • 15 -
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 172 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 30 -
To Believe or Not to Believe Your LLM
Paper • 2406.02543 • Published • 35 -
Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
Paper • 2406.06469 • Published • 29 -
HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale
Paper • 2406.19280 • Published • 63 -
Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems
Paper • 2407.01370 • Published • 89 -
Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages
Paper • 2407.03321 • Published • 20 -
Training Task Experts through Retrieval Based Distillation
Paper • 2407.05463 • Published • 10 -
InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct
Paper • 2407.05700 • Published • 14 -
AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?
Paper • 2407.15711 • Published • 9 -
MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
Paper • 2407.20183 • Published • 43 -
OmniParser for Pure Vision Based GUI Agent
Paper • 2408.00203 • Published • 25 -
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
Paper • 2408.06663 • Published • 16 -
To Code, or Not To Code? Exploring Impact of Code in Pre-training
Paper • 2408.10914 • Published • 44 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 133 -
MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
Paper • 2408.13257 • Published • 26 -
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Paper • 2409.01704 • Published • 83 -
ContextCite: Attributing Model Generation to Context
Paper • 2409.00729 • Published • 14 -
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 92 -
A Controlled Study on Long Context Extension and Generalization in LLMs
Paper • 2409.12181 • Published • 45 -
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Paper • 2409.12183 • Published • 39 -
Attention Prompting on Image for Large Vision-Language Models
Paper • 2409.17143 • Published • 7 -
Can Models Learn Skill Composition from Examples?
Paper • 2409.19808 • Published • 10 -
Law of the Weakest Link: Cross Capabilities of Large Language Models
Paper • 2409.19951 • Published • 54 -
LLaVA-Critic: Learning to Evaluate Multimodal Models
Paper • 2410.02712 • Published • 37 -
From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond
Paper • 2411.03590 • Published • 10 -
Autoregressive Models in Vision: A Survey
Paper • 2411.05902 • Published • 19 -
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Paper • 2411.07133 • Published • 38 -
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Paper • 2501.05452 • Published • 15 -
Demystifying Domain-adaptive Post-training for Financial LLMs
Paper • 2501.04961 • Published • 11 -
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Paper • 2412.19723 • Published • 87 -
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Paper • 2501.04003 • Published • 27 -
MLLM-as-a-Judge for Image Safety without Human Labeling
Paper • 2501.00192 • Published • 31 -
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong
Paper • 2501.09775 • Published • 33 -
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Paper • 2501.09781 • Published • 28 -
CodeMonkeys: Scaling Test-Time Compute for Software Engineering
Paper • 2501.14723 • Published • 10 -
s1: Simple test-time scaling
Paper • 2501.19393 • Published • 124 -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 62 -
Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
Paper • 2502.01941 • Published • 15 -
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 58 -
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Paper • 2502.01081 • Published • 14 -
Great Models Think Alike and this Undermines AI Oversight
Paper • 2502.04313 • Published • 33 -
Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models
Paper • 2502.06755 • Published • 7 -
Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon
Paper • 2502.07445 • Published • 11 -
NoLiMa: Long-Context Evaluation Beyond Literal Matching
Paper • 2502.05167 • Published • 15 -
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper • 2502.14802 • Published • 13 -
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
Paper • 2502.13962 • Published • 28 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 39 -
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper • 2502.12215 • Published • 16 -
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Paper • 2502.11196 • Published • 23 -
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Paper • 2502.08826 • Published • 17 -
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Paper • 2502.11831 • Published • 20 -
Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
Paper • 2502.09083 • Published • 4 -
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper • 2502.14499 • Published • 192 -
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Paper • 2502.08235 • Published • 58 -
VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
Paper • 2502.12084 • Published • 31 -
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
Paper • 2502.14302 • Published • 9 -
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Paper • 2502.19361 • Published • 28 -
VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model
Paper • 2502.18906 • Published • 12 -
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
Paper • 2502.17535 • Published • 8 -
MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Paper • 2502.17422 • Published • 7 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 49 -
AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
Paper • 2503.02268 • Published • 11 -
LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation
Paper • 2503.02972 • Published • 25 -
How to Steer LLM Latents for Hallucination Detection?
Paper • 2503.01917 • Published • 11 -
On the Acquisition of Shared Grammatical Representations in Bilingual Language Models
Paper • 2503.03962 • Published • 4 -
Where do Large Vision-Language Models Look at when Answering Questions?
Paper • 2503.13891 • Published • 8 -
Can Large Vision Language Models Read Maps Like a Human?
Paper • 2503.14607 • Published • 10 -
UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning
Paper • 2503.21620 • Published • 62 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 119 -
Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
Paper • 2504.00294 • Published • 10 -
What Makes a Good Natural Language Prompt?
Paper • 2506.06950 • Published • 11 -
Hidden in plain sight: VLMs overlook their visual representations
Paper • 2506.08008 • Published • 7 -
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Paper • 2506.11928 • Published • 23 -
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper • 2506.14245 • Published • 42 -
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79 -
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
Paper • 2507.19478 • Published • 30 -
Attention Basin: Why Contextual Position Matters in Large Language Models
Paper • 2508.05128 • Published • 4 -
Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
Paper • 2508.02120 • Published • 19 -
Ovis2.5 Technical Report
Paper • 2508.11737 • Published • 109 -
UItron: Foundational GUI Agent with Advanced Perception and Planning
Paper • 2508.21767 • Published • 12 -
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Paper • 2509.19284 • Published • 22 -
Video models are zero-shot learners and reasoners
Paper • 2509.20328 • Published • 96 -
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
Paper • 2510.24563 • Published • 22