SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement
arXiv:2607.18960v1 Announce Type: cross Abstract: Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether…
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
arXiv:2607.18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their…
Alignment of a Total Automation Economy
arXiv:2607.17015v2 Announce Type: replace-cross Abstract: We consider economic theory from the perspective of a total automation economy, one with no…
Rater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v1 Announce Type: new Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels…
When Does Muon Help Agentic Reinforcement Learning?
arXiv:2607.16169v2 Announce Type: replace-cross Abstract: Muon is competitive with AdamW in large-scale pre-training, but its value for reinforcement-learning (RL) post-training…
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…
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…
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…
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…
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…