A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
Paper • 2312.08578 • Published • 20
paper2read
-
-
ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks
Paper • 2312.08583 • Published • 11 -
Vision-Language Models as a Source of Rewards
Paper • 2312.09187 • Published • 12 -
StemGen: A music generation model that listens
Paper • 2312.08723 • Published • 48 -
Pearl: A Production-ready Reinforcement Learning Agent
Paper • 2312.03814 • Published • 15 -
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
Paper • 2312.13789 • Published • 15 -
PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation
Paper • 2312.17276 • Published • 16 -
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Paper • 2204.05862 • Published • 3 -
Improving Text Embeddings with Large Language Models
Paper • 2401.00368 • Published • 82 -
DocLLM: A layout-aware generative language model for multimodal document understanding
Paper • 2401.00908 • Published • 191 -
Understanding LLMs: A Comprehensive Overview from Training to Inference
Paper • 2401.02038 • Published • 65 -
A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA
Paper • 2312.03732 • Published • 12 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 123 -
MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
Paper • 2401.04081 • Published • 74 -
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon
Paper • 2401.03462 • Published • 29 -
MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation
Paper • 2401.04468 • Published • 49 -
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Paper • 2401.04658 • Published • 27 -
Masked Audio Generation using a Single Non-Autoregressive Transformer
Paper • 2401.04577 • Published • 44 -
Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
Paper • 2401.05811 • Published • 9 -
Self-Instruct: Aligning Language Model with Self Generated Instructions
Paper • 2212.10560 • Published • 9 -
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
Paper • 2401.08671 • Published • 15 -
Scalable Pre-training of Large Autoregressive Image Models
Paper • 2401.08541 • Published • 38 -
DiffusionGPT: LLM-Driven Text-to-Image Generation System
Paper • 2401.10061 • Published • 31 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 153 -
Zero Bubble Pipeline Parallelism
Paper • 2401.10241 • Published • 25 -
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper • 2401.10774 • Published • 60 -
Lost in the Middle: How Language Models Use Long Contexts
Paper • 2307.03172 • Published • 44 -
AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
Paper • 2401.12963 • Published • 12 -
Lumiere: A Space-Time Diffusion Model for Video Generation
Paper • 2401.12945 • Published • 86 -
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Paper • 2311.16502 • Published • 40 -
Proactive Detection of Voice Cloning with Localized Watermarking
Paper • 2401.17264 • Published • 19 -
LongAlign: A Recipe for Long Context Alignment of Large Language Models
Paper • 2401.18058 • Published • 24 -
MobileDiffusion: Subsecond Text-to-Image Generation on Mobile Devices
Paper • 2311.16567 • Published • 20 -
A Long Way to Go: Investigating Length Correlations in RLHF
Paper • 2310.03716 • Published • 10 -
Efficient Exploration for LLMs
Paper • 2402.00396 • Published • 22 -
Transforming and Combining Rewards for Aligning Large Language Models
Paper • 2402.00742 • Published • 12 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 53 -
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
Paper • 2402.10176 • Published • 38 -
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
Paper • 2309.14509 • Published • 22 -
MambaByte: Token-free Selective State Space Model
Paper • 2401.13660 • Published • 59 -
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Paper • 2311.03285 • Published • 30 -
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Paper • 2309.12307 • Published • 89 -
NExT-GPT: Any-to-Any Multimodal LLM
Paper • 2309.05519 • Published • 79 -
Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
Paper • 2401.16158 • Published • 20 -
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Paper • 2403.07816 • Published • 45 -
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Paper • 2403.09611 • Published • 129 -
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
Paper • 2402.09844 • Published • 21 -
Llama 2: Open Foundation and Fine-Tuned Chat Models
Paper • 2307.09288 • Published • 251 -
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
Paper • 2404.14619 • Published • 126 -
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 80 -
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
Paper • 2402.14905 • Published • 134 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 145 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
LoRA Learns Less and Forgets Less
Paper • 2405.09673 • Published • 91 -
Pheme: Efficient and Conversational Speech Generation
Paper • 2401.02839 • Published • 18 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 41 -
Parrot: Enhancing Multi-Turn Chat Models by Learning to Ask Questions
Paper • 2310.07301 • Published • 1 -
Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
Paper • 2405.11273 • Published • 19 -
SimPO: Simple Preference Optimization with a Reference-Free Reward
Paper • 2405.14734 • Published • 12 -
Aligning Large Multimodal Models with Factually Augmented RLHF
Paper • 2309.14525 • Published • 32 -
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Paper • 2310.11511 • Published • 80 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 33 -
Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step
Paper • 2406.04314 • Published • 30 -
Scalable Diffusion Models with Transformers
Paper • 2212.09748 • Published • 17 -
Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
Paper • 2402.14740 • Published • 18 -
RewardBench: Evaluating Reward Models for Language Modeling
Paper • 2403.13787 • Published • 22 -
An Introduction to Vision-Language Modeling
Paper • 2405.17247 • Published • 90 -
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
Paper • 2311.06242 • Published • 96 -
Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
Paper • 2406.02430 • Published • 38 -
MobileVLM : A Fast, Reproducible and Strong Vision Language Assistant for Mobile Devices
Paper • 2312.16886 • Published • 22 -
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Paper • 2402.03766 • Published • 15 -
Qwen2 Technical Report
Paper • 2407.10671 • Published • 171 -
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 72 -
Imagen 3
Paper • 2408.07009 • Published • 62 -
xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
Paper • 2408.08872 • Published • 101 -
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
Paper • 2407.19669 • Published • 26 -
Building and better understanding vision-language models: insights and future directions
Paper • 2408.12637 • Published • 133 -
Generative Verifiers: Reward Modeling as Next-Token Prediction
Paper • 2408.15240 • Published • 13 -
Language Model Can Listen While Speaking
Paper • 2408.02622 • Published • 40 -
WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
Paper • 2409.03753 • Published • 19 -
LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Paper • 2409.06666 • Published • 60 -
MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis
Paper • 2409.07129 • Published • 8 -
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Paper • 2409.01704 • Published • 83 -
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Paper • 2409.12191 • Published • 79 -
Prithvi WxC: Foundation Model for Weather and Climate
Paper • 2409.13598 • Published • 45 -
Baichuan-Omni Technical Report
Paper • 2410.08565 • Published • 87 -
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Paper • 2410.08146 • Published • 1 -
Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
Paper • 2410.16153 • Published • 44 -
Baichuan Alignment Technical Report
Paper • 2410.14940 • Published • 51 -
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
Paper • 2410.13861 • Published • 56 -
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
Paper • 2404.05719 • Published • 83 -
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Paper • 2410.18451 • Published • 21 -
Continuous Speech Synthesis using per-token Latent Diffusion
Paper • 2410.16048 • Published • 30 -
Fast Best-of-N Decoding via Speculative Rejection
Paper • 2410.20290 • Published • 10 -
Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
Paper • 2410.21845 • Published • 16 -
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
Paper • 2410.19609 • Published • 18 -
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
Paper • 2410.20424 • Published • 40 -
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
Paper • 2410.22304 • Published • 18 -
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Paper • 2410.22391 • Published • 22 -
TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Paper • 2410.23168 • Published • 24 -
Stealing User Prompts from Mixture of Experts
Paper • 2410.22884 • Published • 16 -
LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning
Paper • 2410.02884 • Published • 54 -
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Paper • 2411.02265 • Published • 25 -
Watermark Anything with Localized Messages
Paper • 2411.07231 • Published • 21 -
LLaVA-o1: Let Vision Language Models Reason Step-by-Step
Paper • 2411.10440 • Published • 129 -
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
Paper • 2411.14405 • Published • 61 -
Multimodal Autoregressive Pre-training of Large Vision Encoders
Paper • 2411.14402 • Published • 47 -
SpiRit-LM: Interleaved Spoken and Written Language Model
Paper • 2402.05755 • Published • 15 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 135 -
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Paper • 2412.10360 • Published • 147 -
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 163 -
A Survey of Small Language Models
Paper • 2410.20011 • Published • 46 -
Qwen2.5 Technical Report
Paper • 2412.15115 • Published • 377 -
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 192 -
DynaSaur: Large Language Agents Beyond Predefined Actions
Paper • 2411.01747 • Published • 37 -
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 63 -
Solving math word problems with process- and outcome-based feedback
Paper • 2211.14275 • Published • 10 -
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Paper • 2203.11171 • Published • 5 -
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Paper • 2501.03262 • Published • 104 -
A2C is a special case of PPO
Paper • 2205.09123 • Published • 2 -
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper • 2501.04519 • Published • 290 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 104 -
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Paper • 2412.06559 • Published • 86 -
CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
Paper • 2411.12644 • Published • 6 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 55 -
DeepSeek-V3 Technical Report
Paper • 2412.19437 • Published • 82 -
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Paper • 2501.11873 • Published • 68 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario
Paper • 2501.10132 • Published • 22 -
Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models
Paper • 2407.01906 • Published • 46 -
LIMA: Less Is More for Alignment
Paper • 2305.11206 • Published • 27 -
Chain-of-Retrieval Augmented Generation
Paper • 2501.14342 • Published • 58 -
Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch
Paper • 2501.18512 • Published • 29 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper • 2501.17161 • Published • 125 -
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Paper • 2502.02492 • Published • 66 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 100 -
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 90 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 217 -
SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound
Paper • 2405.00233 • Published • 17 -
R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning
Paper • 2503.05379 • Published • 38 -
Learning from Failures in Multi-Attempt Reinforcement Learning
Paper • 2503.04808 • Published • 18 -
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Paper • 2503.06749 • Published • 31 -
Gemini Embedding: Generalizable Embeddings from Gemini
Paper • 2503.07891 • Published • 46 -
Charting and Navigating Hugging Face's Model Atlas
Paper • 2503.10633 • Published • 93 -
Modifying Large Language Model Post-Training for Diverse Creative Writing
Paper • 2503.17126 • Published • 36 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 305 -
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Paper • 2504.02587 • Published • 32 -
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Paper • 2504.05599 • Published • 86 -
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Paper • 2504.04842 • Published • 35 -
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Paper • 2503.14476 • Published • 146 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 63 -
UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning
Paper • 2503.21620 • Published • 62 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 141 -
The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks
Paper • 2504.15521 • Published • 64 -
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
Paper • 2504.16078 • Published • 21 -
Reasoning Models Can Be Effective Without Thinking
Paper • 2504.09858 • Published • 12 -
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Paper • 2505.07293 • Published • 28 -
Seed1.5-VL Technical Report
Paper • 2505.07062 • Published • 157 -
DreamO: A Unified Framework for Image Customization
Paper • 2504.16915 • Published • 24 -
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
Paper • 2505.07916 • Published • 135 -
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective
Paper • 2505.15045 • Published • 56 -
Scaling Law for Quantization-Aware Training
Paper • 2505.14302 • Published • 76 -
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Paper • 2505.15277 • Published • 105 -
Efficient Agent Training for Computer Use
Paper • 2505.13909 • Published • 44 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 98 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Paper • 2505.22617 • Published • 132 -
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Paper • 2401.18059 • Published • 48 -
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Paper • 2506.05301 • Published • 59 -
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
Paper • 2504.07096 • Published • 77 -
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
Paper • 2508.13167 • Published • 129 -
Step-Audio 2 Technical Report
Paper • 2507.16632 • Published • 74 -
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Paper • 2508.16279 • Published • 61 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 265 -
Group Sequence Policy Optimization
Paper • 2507.18071 • Published • 320 -
Neural Discrete Representation Learning
Paper • 1711.00937 • Published -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 172 -
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Paper • 2211.05100 • Published • 37 -
Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates
Paper • 2509.09550 • Published • 4 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 27 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
Robust Speech Recognition via Large-Scale Weak Supervision
Paper • 2212.04356 • Published • 53 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 56