The rapid scaling of large language models (LLMs) has unlocked remarkable capabilities across various domains. However, deploying LLMs on mobile devices remains challenging because of their high computational and memory requirements. Low-bit quantization (e.g., 4-bit weights, 8-bit activations) can reduce model size wh...
Hang-Yu Zheng, Zhi-Hao Shu, Kun-Xiong Zhu et al.· Proceedings of the 32nd ACM...· 0 citations
Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test t...
Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang et al.· 2 citations
Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disclose which concepts have been removed, and even with access to the original base model, an adversary may still lack a clear target to attack...
Kai-Yuan Deng, Yu-Chen Li, Yang Xiao et al.· 1 citation
Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods intervene at the text interface, through prompt modification or localized updates to text-conditioning weights, and they are evaluated by what the model outputs for given prom...
Kai-Yuan Deng, Yu-Chen Li, Gen Li et al.· 1 citation
LAM is proposed, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a pe...
Bai-Xi Sun, Le Chen, Anjir Ahmed Chowdhury et al.· 0 citations
HPD-Parsing is introduced, which replaces full-page autoregressive generation with a Hierarchical Parallel Decoding paradigm, and establishes hierarchical parallel decoding as an effective alternative to full-page autoregressive generation, opening a new direction for efficient unified document parsing.
This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents, finding that semantically different working-memory objects exhibit distinct retention and compression behavior.
Le Chen, Zi-Shen Wan, Bai-Xi Sun et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
