Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale plausibility without verifying the underlying acoustic evidence. To address this issue, we first introduce spoofing evidence-grounded audio reasoning (SEAR), a four-task AQA...
Rong-Zheng-Wang-Lian-Hui-Liu-Cheng-De-Wang-Qin-Yun Wan, Su-Liu Qin, Jia-Xi Li et al.· 0 citations
Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored decision axis: after choosing a model, a client must still choose which provider serves it. Measuring live endpoints across [nummodels] open models, competing providers,...
Liang He, Jing Wen, Yi-Xiong Chen et al.· 0 citations
Grounded Checklist Partial Credit (GCPC) is introduced, a human-governed and LLM-instantiated partial-credit evaluation of agent trajectories that better discriminates official PASS and FAIL outcomes than holistic judging on the shared subset.
Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge. Although recent work has substantially improved skill retrieval due to the increasing skill libraries, retrieving a plausible skill bundle does not guarantee that executing it is worthwhile. Since every ski...
CRIP, a personalized OSFL framework that operates in the representation space via channel-level feature alignment, consistently outperforms local models and state-of-the-art baselines, validating the effectiveness of representation-space personalization under extreme domain heterogeneity.
Zijian Jiang, Chaoli Sun, Han-Ding Wang et al.· 0 citations
Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed compute budget, implicitly assuming that all errors carry equal cost. However, the consequence of an incorrect prediction on downstream tas...
Jing Wen, Liang He, Mingyu Cao 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.
