arXiv AI
Jun 30
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
arXiv:2604. 04385v5 Announce Type: replace-cross Abstract: We localize the policy routing mechanism in alignment-trained language models.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 30
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
arXiv:2606. 29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof.
arXiv AI
Jun 30
It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents
arXiv:2606. 27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications.
arXiv AI
Jun 30
Open Problems in Constitutional Preference Reconstruction
arXiv:2606. 30116v1 Announce Type: new Abstract: Pairwise preference data is widely used for training and evaluating language models (e.
arXiv AI
Jun 30
Langshaw: Declarative Interaction Protocols Based on Sayso and Conflict
arXiv:2606. 29601v1 Announce Type: cross Abstract: Current languages for specifying multiagent protocols either over-constrain protocol enactments or complicate capturing their meanings.
arXiv AI
Jun 30
VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction
arXiv:2606. 29548v1 Announce Type: cross Abstract: Driver decision making in the dilemma zone at signalized intersections is safety critical, as vehicles approaching a yellow signal must decide whether to stop or proceed within limited time and distance margins.
arXiv AI
Jun 30
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
arXiv:2606. 22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget.
arXiv Machine Learning
Jun 30
Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics
arXiv:2606. 30509v1 Announce Type: new Abstract: Matrix factorization (i.
arXiv AI
Jun 30
Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
arXiv:2604. 19971v2 Announce Type: replace-cross Abstract: Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking.
arXiv Machine Learning
Jun 30
Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models
arXiv:2606. 29196v1 Announce Type: new Abstract: Do language models know when they are being tested?
arXiv Machine Learning
Jun 30
Generalization error of min-norm interpolators in transfer learning
arXiv:2406. 13944v2 Announce Type: replace-cross Abstract: This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available.
arXiv AI
Jun 30
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
arXiv:2606. 30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while the latent properties they are meant to represent remain difficult to verify.
arXiv AI
Jun 30
Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation
arXiv:2606. 28998v1 Announce Type: cross Abstract: Large Language Model (LLM) alignment trains an LLM using preference data to produce outputs that better meet established quality standards.
arXiv AI
Jun 30
High-Dimensional Concentration and Retrieval Instability in Embedding Spaces: Implications for Retrieval-Augmented Generation
arXiv:2606. 28330v1 Announce Type: cross Abstract: Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance.
arXiv AI
Jun 30
Robust Multi-Agent LLMs under Byzantine Faults
arXiv:2605. 09076v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability.
arXiv AI
Jun 30
RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation
arXiv:2606. 28410v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding.
arXiv AI
Jun 30
AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors
arXiv:2606. 28416v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipulations and imperceptible perturbations that can lead to erroneous predictions.
arXiv AI
Jun 30
RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis
arXiv:2606. 28385v1 Announce Type: cross Abstract: Recent advances in robot world models enable synthetic video generation for embodied prediction and planning.
arXiv AI
Jun 30
An Integrated Machine Learning and Hierarchical Variance Decomposition Pipeline for Student Performance Prediction and Metacognitive Calibration on Multi-Signal Telemetry
arXiv:2606. 28881v1 Announce Type: cross Abstract: Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems.
arXiv AI
Jun 30
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
arXiv:2606. 28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain.