Papers

CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

Efficient Agents: Building Effective Agents While Reducing Cost

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

VeriGUI: Verifiable Long-Chain GUI Dataset

Qwen2.5-VL Technical Report

The GAN is dead; long live the GAN! A Modern GAN Baseline

MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

NVILA: Efficient Frontier Visual Language Models

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Baichuan-Omni Technical Report

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Emu3: Next-Token Prediction is All You Need

CogVLM2: Visual Language Models for Image and Video Understanding

Qwen2 Technical Report

An Image is Worth 32 Tokens for Reconstruction and Generation

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

FIFO-Diffusion: Generating Infinite Videos from Text without Training

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

OmniFusion Technical Report

PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition

Machine learning prediction errors better than DFT accuracy

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience

AMix-1: A Pathway to Test-Time Scalable Protein Foundation Model

CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search

Representation Shift: Unifying Token Compression with FlashAttention

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward