Huiqiang Jiang

TriangleMix: Accelerating Prefilling via Decoding-time Contribution Sparsity

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

SortedRL: Accelerating RL Training for LLMs through Online Length-aware Scheduling

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention

Chain-of-Model Learning for Language Model

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension

Zoomer: Enhancing MLLM Performance with Adaptive Image Focus Optimization