Enhancing Rubric-based RL via Self-Distillation
arXiv:2607.18082v2 Announce Type: replace-cross Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized…
SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI
arXiv:2607.18239v1 Announce Type: new Abstract: Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond…
DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification
arXiv:2508.12745v2 Announce Type: replace-cross Abstract: Image set classification (ISC), which can be viewed as a task of comparing similarities between…
Breaking the Factorization Barrier in Diffusion Language Models
arXiv:2603.00045v3 Announce Type: replace-cross Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the…
AI sustains higher strategic tension than humans in chess
arXiv:2508.13213v4 Announce Type: replace Abstract: Strategic decision-making requires balancing immediate opportunities against long-term objectives: a tension fundamental to competitive environments.…
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning — The Limit of the Scaling Law
arXiv:2606.26454v2 Announce Type: replace Abstract: By promoting vectors to spheres and enabling explicit model construction, neural networks can perform symbolic-level…
Uncovering Latent Reasoning Strategies in Language Models
arXiv:2607.17674v1 Announce Type: cross Abstract: A language model $p_theta(y mid x)$ trained on reasoning tasks learns to solve problems via…
Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models
arXiv:2607.15893v2 Announce Type: replace-cross Abstract: While the internal mechanisms of autoregressive (AR) transformers have been studied extensively, much less is…
CoEvoP&R: Co-Evolving Placement Objectives with Routing Feedback via Large Language Models
arXiv:2607.17398v1 Announce Type: cross Abstract: Analytical placers rely on differentiable objective functions to guide placement, typically combining intermediate surrogate metrics…
Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones
arXiv:2607.17419v1 Announce Type: cross Abstract: Linear attention promises constant-time recurrent inference but degrades sharply on associative recall. We formulate attention…