Instruction Pre-Training: Language Models are Supervised Multitask Learners
Paper • 2406.14491 • Published • 96
DS' Daily paper
-
-
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 68 -
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
Paper • 2405.20541 • Published • 24 -
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Paper • 2406.01574 • Published • 54 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 33 -
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
Paper • 2406.00392 • Published • 14 -
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Paper • 2406.01014 • Published • 33 -
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper • 2406.02657 • Published • 41 -
Parrot: Multilingual Visual Instruction Tuning
Paper • 2406.02539 • Published • 36 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 59 -
Large Language Model Confidence Estimation via Black-Box Access
Paper • 2406.04370 • Published • 22 -
CRAG -- Comprehensive RAG Benchmark
Paper • 2406.04744 • Published • 46 -
PowerInfer-2: Fast Large Language Model Inference on a Smartphone
Paper • 2406.06282 • Published • 39 -
Are We Done with MMLU?
Paper • 2406.04127 • Published • 39 -
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Paper • 2406.07522 • Published • 40 -
Transformers meet Neural Algorithmic Reasoners
Paper • 2406.09308 • Published • 44 -
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Paper • 2406.11931 • Published • 69 -
Bootstrapping Language Models with DPO Implicit Rewards
Paper • 2406.09760 • Published • 41 -
TroL: Traversal of Layers for Large Language and Vision Models
Paper • 2406.12246 • Published • 36 -
VoCo-LLaMA: Towards Vision Compression with Large Language Models
Paper • 2406.12275 • Published • 31 -
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Paper • 2406.15319 • Published • 64 -
Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
Paper • 2406.12624 • Published • 37 -
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Paper • 2406.17557 • Published • 102 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 64 -
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Paper • 2308.01825 • Published • 23 -
SLiC-HF: Sequence Likelihood Calibration with Human Feedback
Paper • 2305.10425 • Published • 7 -
RATIONALYST: Pre-training Process-Supervision for Improving Reasoning
Paper • 2410.01044 • Published • 35 -
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Paper • 2410.23090 • Published • 55 -
LLaMo: Large Language Model-based Molecular Graph Assistant
Paper • 2411.00871 • Published • 22 -
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 11 -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 7 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 162 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 253 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 126