Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL causes policy mode collapse even under reference KL or entropy regularization, reducing the policy to a single high-reward mode. In T2I, thi...
Zhi-Yuan Ma, Jia-Ming Li, Ling-Zhen Li et al.· 0 citations
This work presents the first music-specific, layer-wise, multi-paradigm empirical study of hallucination in audio-language models and forms it as a hierarchical perceptual grounding failure across five layers: sound events, temporal properties, tonal attributes, style, and emotion.
Yu Liu, Jia-Hui Liu, Zhi-Lin Liu et al.· 0 citations
Findings show that historical evidence use should be evaluated under state variation, rather than inferred from outcome-only correctness, and that open-weight models rely heavily on context continuity and are reluctant to spontaneously switch to tool-mediated retrieval when provenance fails.
Yu Liu, Wen-Xiao Zhang, Cheng Hu et al.· 0 citations
CARE (Canonicalization, Attribution, and Resolution Engine), a shell-specific, static-first verifier for individual shell commands before execution can reduce dispatch-boundary risk for LLM agents while preserving most benign workflows.
Yu Liu, Wenxiao Zhang, Zhiwei Yang et al.· arXiv.org· 1 citation
Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end language models while providing evidence coverage and paragraph-referenced reasoning traces.
Ji-Hao Zhu, Zhi-Wei Yang, Wen-Xiao Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
