arXiv Machine Learning
Jun 29
Qwen-Image-2.0-RL Technical Report
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 29
iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework
arXiv:2409. 13007v3 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge in classification tasks, often causing standard learning algorithms to become biased toward the majority class.
arXiv AI
Jun 29
Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
arXiv:2605. 05092v2 Announce Type: replace-cross Abstract: Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions.
arXiv AI
Jun 29
Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.
arXiv AI
Jun 29
Deep Neural Networks Inspired by Differential Equations
arXiv:2510. 09685v2 Announce Type: replace-cross Abstract: Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines.
arXiv AI
Jun 29
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
arXiv:2604. 03401v4 Announce Type: replace-cross Abstract: Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns.
arXiv AI
Jun 29
MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
arXiv:2603. 03710v3 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness.
arXiv AI
Jun 29
Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives
arXiv:2606. 28217v1 Announce Type: cross Abstract: We propose a framework for reward allocation in fully delegated AI cooperatives where humans are represented by agents that contribute data and participate in model updates under heterogeneous value constraints.
arXiv AI
Jun 29
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
arXiv:2510. 10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs).
arXiv AI
Jun 29
SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
arXiv:2507. 18632v2 Announce Type: replace-cross Abstract: Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data.
arXiv AI
Jun 29
DMind Benchmark: Toward a Holistic Assessment of LLM Capabilities across the Web3 Domain
arXiv:2504. 16116v4 Announce Type: replace-cross Abstract: The Web3 ecosystem, underpinned by cryptographic primitives and decentralized consensus, represents a high-stakes environment where software vulnerabilities and incentive misalignments translate directly into financial loss.
arXiv AI
Jun 29
What the LLM Should Not Say: Boundary-Aware Context Grounding for A Seven-Channel EEG Agent
arXiv:2606. 26519v2 Announce Type: replace Abstract: Large language models (LLMs) can make scientific software easier to use.
arXiv AI
Jun 29
VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring
arXiv:2606. 27941v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) provide useful decompositions of Transformer residual streams, but their learned features are usually named post hoc rather than directly connected to the Transformer's token vocabulary.
arXiv AI
Jun 29
CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association
arXiv:2606. 28179v1 Announce Type: cross Abstract: Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular research and reliable risk stratification.
arXiv AI
Jun 29
Higher-Order Fourier Neural Operator: Explicit Mode Mixer for Nonlinear PDEs
arXiv:2606. 28122v1 Announce Type: cross Abstract: Neural operators provide deep neural networks for learning mappings between function spaces.
arXiv AI
Jun 29
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
arXiv:2606. 28128v1 Announce Type: cross Abstract: Video generation models have emerged as a promising paradigm for embodied world simulation.
arXiv AI
Jun 29
STAG: Spatio-temporal Evolving Structural Representation of Action Units for Micro-expression Recognition
arXiv:2606. 28083v1 Announce Type: cross Abstract: Micro-expression recognition is challenging due to subtle and short-lived facial muscle movements.
arXiv AI
Jun 29
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
arXiv:2606. 27922v1 Announce Type: cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal parameters.
arXiv AI
Jun 29
Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF
arXiv:2606. 27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal.
arXiv Machine Learning
Jun 29
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
arXiv:2606. 27771v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy.