arXiv:2601.21647v1 Announce Type: cross Abstract: Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level guidance procedures or trajectory optimization mechanisms. In this work, we introduce Iterative Latent Representation Refinement (ILRR), a learning-free framework for steering DLMs using a […]
GUIGuard: Toward a General Framework for Privacy-Preserving GUI Agents
arXiv:2601.18842v2 Announce Type: replace-cross Abstract: GUI agents enable end-to-end automation through direct perception of and interaction with on-screen interfaces. However, these agents frequently access interfaces containing sensitive personal information, and screenshots are often transmitted to remote models, creating substantial privacy risks. These risks are particularly severe in GUI workflows: GUIs expose richer, more accessible private […]
Gauge-invariant representation holonomy
arXiv:2601.21653v1 Announce Type: cross Abstract: Deep networks learn internal representations whose geometry–how features bend, rotate, and evolve–affects both generalization and robustness. Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation sets, but miss how representations change along input paths. Two models may appear nearly identical under these metrics yet respond very […]
SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction
arXiv:2601.18537v2 Announce Type: replace-cross Abstract: Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods often struggle to maintain global directional consistency, leading to drifting or implausible trajectories when extrapolated over long time horizons. To address this issue, we propose a semantic-key-point-conditioned trajectory modeling framework, […]
AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context
arXiv:2601.19494v2 Announce Type: replace-cross Abstract: High-quality evaluation benchmarks are pivotal for deploying Large Language Models (LLMs) in Automated Code Review (ACR). However, existing benchmarks suffer from two critical limitations: first, the lack of multi-language support in repository-level contexts, which restricts the generalizability of evaluation results; second, the reliance on noisy, incomplete ground truth derived from […]
MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging
arXiv:2601.15930v2 Announce Type: replace-cross Abstract: Model merging (MM) offers an efficient mechanism for integrating multiple specialized models without access to original training data or costly retraining. While MM has demonstrated success in domains like computer vision, its role in recommender systems (RSs) remains largely unexplored. Recently, Generative Recommendation (GR) has emerged as a new paradigm […]
When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Market Outcomes and Adoption
arXiv:2601.21650v1 Announce Type: cross Abstract: AI consumer markets are characterized by severe buyer-supplier market asymmetries. Complex AI systems can appear highly accurate while making costly errors or embedding hidden defects. While there have been regulatory efforts surrounding different forms of disclosure, large information gaps remain. This paper provides the first experimental evidence on the important […]
Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models
arXiv:2601.12247v2 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches. However, current decoding strategies often adopt a reactive stance, underutilizing the global bidirectional context to dictate global trajectories. To address this, we propose Plan-Verify-Fill (PVF), a training-free paradigm that grounds planning via […]
Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
arXiv:2601.21919v1 Announce Type: new Abstract: The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcement learning (RL)-based solutions tackle this problem by coupling a length penalty with outcome-based rewards. This simplistic reward weighting struggles to reconcile brevity with accuracy, as enforcing brevity may […]
SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification
arXiv:2601.21561v1 Announce Type: cross Abstract: Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we propose Selective Adaptive Learning (SAL), a training method that combines selective parameter activation with adaptive area partitioning. Specifically, SAL decomposes the […]
IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
arXiv:2510.25262v2 Announce Type: replace-cross Abstract: Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stabilizing training without controlling how representations capture task-relevant information. We propose IB-Inspired Normalization (IBNorm), a simple yet powerful family of methods grounded in the Information Bottleneck […]
When Does Adaptation Win? Scaling Laws for Meta-Learning in Quantum Control
arXiv:2601.18973v2 Announce Type: replace-cross Abstract: Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales […]