11 papers
Recursive Environment Scaling for General Long-Horizon Agents
Lingxiao Jing, Zhengbo Jiao, Yichen Xiang +10
We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environment Scaling (RES), transform…
SLDBench v2: Active Scaling Law Discovery
Lingbei Meng, Rui Huang, Zhirong Shen +5
Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests whether language-model agents can…
Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache
Zhirong Shen, Rui Huang, Chang Zou +10
Diffusion Transformers have become the dominant paradigm in generative AI, but their high computational costs severely hinder real-time applications. Prediction-based feature cachi…
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
Tinghao Wang, Yichen Guo, Rui Huang +13
Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introdu…
HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
Peize He, Yaodi Luo, Xiaoqian Liu +7
Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an…
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Chenxi Li, Xianggan Liu, Dake Shen +9
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elici…
MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference
Zitong Xu, Dake Shen, Yaosong Du +3
Recent advances in AIGC (Artificial Intelligence Generated Content) models have enabled significant progress in image and video generation. However, users still struggle to obtain…
Medical priority fusion: achieving dual optimization of sensitivity and interpretability in nipt anomaly detection
Xiuqi Ge, Zhibo Yao, Yaosong Du
Clinical machine learning faces a critical dilemma in high-stakes medical applications: algorithms achieving optimal diagnostic performance typically sacrifice the interpretability…
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
Chenxi Li, Yichen Guo, Benfang Qian +5
Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content that is grammatic…
Enhancing LLMs in Long Code Translation through Instrumentation and Program State Alignment
Li Xin-Ye, Du Ya-Li, Li Ming
Code translation aims to transform code between programming languages while preserving functionality, with applications in cross-platform development and software migration. Recent…
Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals
Hanze Li, Yaosong Du, Zhibo Yao +3
Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. Howeve…