Yiran Chen

Vision-Zero: Scalable VLM Self-Evolution via Multi-Agent Self-Play

IncVGGT: Incremental VGGT for Memory-Bounded Long-Range 3D Reconstruction

DPad: Efficient Diffusion Language Models with Suffix Dropout

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

Accelerating Discrete Diffusion Decoding with Parallel Scan

Accelerating Denoising Generative Models is as Easy as Predicting Second-Order Difference

LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

SELECT: Search-Enhanced Language Models for Analog Circuit Topology Generation

PolyAudio: Advancing Multi-Audio Analysis & Reasoning in Large Audio Language Models

Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Group Distributionally Robust Dataset Distillation with Risk Minimization

CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

SADA: Stability-guided Adaptive Diffusion Acceleration

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training

Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training

CONCORD: Concept-informed Diffusion for Dataset Distillation

Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback