Yao Hu

RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data

WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning

Agentic Analogical Reasoning for Large Language Models

GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

Interleaving Reasoning for Better Text-to-Image Generation

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL

PatternKV: Flattening KV Representation Expands Quantization Headroom

CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression

Cross-Scenario Unified Modeling of User Interests at Billion Scale

LEMUR: Leveraging Vision-Language Models for Fine-Grained Multimodal Retrieval

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

InsBank: Evolving Instruction Subset for Ongoing Alignment

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Model Evaluation