6 papers
SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks
Zhuang Zhuang, Zhipeng Wei, Ji Dai +4
Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be…
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding
Zheng Wang, Haoran Chen, Haoxuan Qin +3
Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumul…
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3
Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it als…
OneLoc: Geo-Aware Generative Recommender Systems for Local Life Service
Zhipeng Wei, Kuo Cai, Junda She +8
Local life service is a vital scenario in Kuaishou App, where video recommendation is intrinsically linked with store's location information. Thus, recommendation in our scenario i…
Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
Zhipeng Wei, Yuqi Liu, N. Benjamin Erichson
Jailbreaking techniques trick Large Language Models (LLMs) into producing restricted output, posing a potential threat. One line of defense is to use another LLM as a Judge to eval…