52 papers
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
Wanshun Su, Yang Shi, Feihu Liu +10
Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio tok…
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation
Keqin Peng, Chen Li, Yuanxin Ouyang +2
On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxicall…
Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models
Shengsheng Zhou, Shuai Wang, Liang Ding +5
Large language models (LLMs) have shown strong performance in automated code generation, with few-shot prompting widely used for its simplicity and effectiveness. However, few-shot…
Grounded Scaling: Why Agentic AI Needs Deterministic Environments
Liang Ding, Xintong Wang
Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-step determinism , -step chain success degrades as . The AGI-t…
Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports
Qingyu Lu, Ruochen Li, Liang Ding +3
Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect…
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products
Haonan Qi, Jin Cao, Yongqi Zhang +9
Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These…