Data Selection via Optimal Control for Language Models

GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Ion Stoica

Research author

Fast Video Generation with Sliding Tile Attention

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Yanzhao Zhang

Research author

E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search

E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model

Yuanxing Zhang

Research author

MIO: A Foundation Model on Multimodal Tokens

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Creativity in LLM-based Multi-Agent Systems: A Survey

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining

Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought

Jinhua Zhao

Research author

Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

Rama Chellappa

Research author

World-in-World: World Models in a Closed-Loop World