activity
20242026
collaborators

5 papers

cs.CV2026

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

Xinming Wang, Weinong Wang, Hongming Yang +13

Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although thes…

cs.LG2026

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

Wenjin Hou, Shangpin Peng, Weinong Wang +13

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model…

cs.CL2025

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs

Hongming Yang, Shi Lin, Jun Shao +4

Lightweight Large Language Models (LwLLMs) are reduced-parameter, optimized models designed to run efficiently on consumer-grade hardware, offering significant advantages in resour…

eess.SP2024

Efffcient Sensing Parameter Estimation with Direct Clutter Mitigation in Perceptive Mobile Networks

Hang Li, Hongming Yang, Qinghua Guo +3

In this work, we investigate sensing parameter estimation in the presence of clutter in perceptive mobile networks (PMNs) that integrate radar sensing into mobile communications. P…

cs.CR2024

Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models

Shi Lin, Peng Qian, Hongming Yang +3

Large language models (LLMs) have achieved remarkable progress across a wide range of applications. Despite advances in safety alignment, they remain vulnerable to jailbreak attack…