arXiv AI
Jun 10
Baseline-Free Policy Optimization for Neural Combinatorial Optimization
arXiv:2606. 10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 10
Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
arXiv:2602. 02788v2 Announce Type: replace-cross Abstract: We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries.
arXiv AI
Jun 10
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
arXiv:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.
arXiv Machine Learning
Jun 10
Gradient-Guided Reward Optimization for Inference-time Alignment
arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.
arXiv AI
Jun 10
An Improved Generative Adversarial Network for Micro-Resistivity Imaging Logging Restoration
arXiv:2606. 10200v1 Announce Type: cross Abstract: An improved GAN-based imaging logging image restoration method is presented in this paper for solving the problem of partially missing micro-resistivity imaging logging images.
arXiv Machine Learning
Jun 10
XtrAIn: Training-Guided Occlusion for Feature Attribution
arXiv:2606. 10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output.
arXiv AI
Jun 10
ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain Resilience
arXiv:2606. 10359v1 Announce Type: new Abstract: AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforcement learning (RL) optimizes flows but is semantically blind to unstructured constraints.
arXiv AI
Jun 10
PromptEmbedder: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
arXiv:2605. 28066v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottlenecks in computational efficiency and cross-architecture transferability.
arXiv AI
Jun 10
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
arXiv:2606. 11019v1 Announce Type: cross Abstract: Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency.
arXiv Machine Learning
Jun 10
LLM-as-a-Discriminator: When Synthetic Tables Still Look Real
arXiv:2606. 09865v1 Announce Type: new Abstract: Privacy and data sharing are often in tension.
arXiv Machine Learning
Jun 10
Encoding the Euler Characteristic Transform
arXiv:2606. 10824v1 Announce Type: new Abstract: The Euler Characteristic Curve (ECC) records the Euler characteristic of a linearly embedded cell complex as a function of filtration height in a given direction, and the Euler Characteristic Transform (ECT) is the injective shape descriptor obtained by collecting ECCs over many directions.
arXiv AI
Jun 10
Representational Alignment with Chemical Induced Fit for Molecular Relational Learning
arXiv:2502. 07027v4 Announce Type: replace-cross Abstract: Molecular Relational Learning (MRL) is widely applied in natural sciences to predict relationships between molecular pairs by extracting structural features.
arXiv AI
Jun 10
A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications
arXiv:2410. 15595v4 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical.
arXiv AI
Jun 10
Assessing Automated Prompt Injection Attacks in Agentic Environments
arXiv:2606. 10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings.
arXiv AI
Jun 10
++nnU-Net: Scaling nnU-Net with Prefix-Based Data Augmentation
arXiv:2606. 10713v1 Announce Type: cross Abstract: The nnU-Net has demonstrated continuous success in medical segmentation tasks, which heavily rely on the availability and diversity of annotated biomedical data.
arXiv Machine Learning
Jun 10
FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses
arXiv:2606. 09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks.
arXiv Machine Learning
Jun 10
Robust Regression of General ReLUs with Queries
arXiv:2606. 11130v1 Announce Type: new Abstract: We study the task of agnostically learning general (as opposed to homogeneous) ReLUs under the Gaussian distribution with respect to the squared loss.
arXiv AI
Jun 10
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
arXiv:2606. 09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive data while preserving model performance.
arXiv Machine Learning
Jun 10
A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations
arXiv:2606. 09894v1 Announce Type: new Abstract: Across contemplative, philosophical, and psychological accounts, human consciousness is often described along a similar spectrum, ranging from reactive and self-focused patterns to more integrative and coherent ones.
arXiv AI
Jun 10
Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation
arXiv:2606. 11127v1 Announce Type: cross Abstract: Synthetic post-training pipelines commonly filter generated samples with reward models or holistic LLM judges, yet two practices remain rarely examined together: whether the filtering signal is grounded in the source evidence that induced each generation, and whether rejected samples can be systematically recovered rather than permanently discarded.