14 papers
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
ZiYi Dong, Yuliang Huang, Weijian Deng +3
This work reformulates language generation as a stochastic optimal control problem, providing a unified theoretical perspective to analyze autoregressive and diffusion models and e…
ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
Kaiwen Luo, Liang Lin, Yibo Zhang +8
Although Audio Large Language Models (ALLMs) have witnessed substantial advancements, their long audio understanding capabilities remain unexplored. A plethora of benchmarks have b…
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Yuchen Cai, Ding Cao, Liang Lin +9
On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and…
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
ShiYing Huang, Liang Lin, Yuer Li +6
In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tensi…
Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
Liang Lin, Miao Yu, Moayad Aloqaily +5
Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigge…
RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
Weijia Liufu, Xiaoyu Guo, Ruiyi Chen +16
Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while…