An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero...
Chubin Zhang, Zheng-Lin Wan, Xing-Rui Yu et al.· 0 citations
Machine learning methods have recently shown promise in predicting composite material properties more efficiently than traditional finite element simulations. However, in real-world applications of composite materials, variations in filler characteristics or processing conditions can cause a significant mismatch betwee...
A. Bhattacharya, Hang-Wei Qian, Sylvain G. Cloutier et al.· Proceedings of the 32nd ACM...· 0 citations
Time-Annealed Perturbation Sampling (TAPS) is proposed, a training-free inference strategy that samples nearby conditioning trajectories through time-aware, manifold-constrained perturbations, and consistently improves semantic and lexical diversity across open-ended and instruction-following generation tasks.
Jing-Xuan Wu, Zheng-Lin Wan, Xing-Rui Yu et al.· 4 citations
This work introduces Relative Generalization Invariance (RGI), the invariance of the validation-loss difference between any two tokens across models, and shows that RGI approximately holds across a wide range of optimizers and moderate architectural variations, suggesting that these choices induce an approximately unif...
Feng-Zhuo Zhang, Shu-Che Wang, Sheng-Gui Li et al.· 0 citations
CUA-Sandbox is introduced, which separates private state capsules from shared runtimes through state-scoped execution and transactional lifecycle operations, including resets and branches, while retaining the original software interfaces and task evaluators.
Xin Yan, Zheng-Bo Jiao, Jia-Qi Liu et al.· 0 citations
The proposed Universal Anchor Representation (UAR), a normalized hierarchical parameterization that constrains inference to bounded coordinates (t,s) \in [0,1]2 while guaranteeing structural connectivity by construction, is paired with a domain-specific language and compiler to produce executable parametric procedural...
Jaeyeon Kim, Po-Yen Lai, J. Wong et al.· Proceedings of the 32nd ACM...· 0 citations
This work proposes an unsupervised PDE-based finetuning framework that eliminates the need for ground-truth solutions, and introduces NSLoRA, a Newton-Schulz orthogonalized variant that rebalances adaptation.
Using an uncertainty-aware physics-informed framework, this work infer future OD flows from area-level counts alone across twelve mobility datasets from cities in the United States and China, reaching accuracy comparable to models that take historical OD matrices as input.
Yi Wang, Jing Li, Jin-Liang Deng et al.· 0 citations
RPS is proposed, a novel training-free decoding method that seeks mid-entropy positions as promising candidate pivots (where to decode), and determines their token assignment that yields the greatest downstream benefit via lookahead evaluation (what to decode).
Yu-Shi Ye, Xu Chen, Hao-Yun Jiang et al.· 1 citation
The results suggest that adaptive reasoning should estimate the future value of computation rather than equating present confidence with correctness, and introduce Adaptive Evidence Residual Allocation (AERA), a sequential controller that learns whether additional computation is likely to recover a better answer from c...
Zimin Wang, I. Tsang, Hang-Wei Qian· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
