AI News

SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning (arxiv.org)

From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model (arxiv.org)

ShelfAware: Real-Time Semantic Localization in Quasi-Static Environments with Low-Cost Sensors (arxiv.org)

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio (arxiv.org)

Calibrating Uncertainty for Zero-Shot Adversarial CLIP (arxiv.org)

Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3) (arxiv.org)

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models (arxiv.org)

MGRegBench: A Novel Benchmark Dataset with Anatomical Landmarks for Mammography Image Registration (arxiv.org)

Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC) (arxiv.org)

Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism (arxiv.org)

Uncovering Competency Gaps in Large Language Models and Their Benchmarks (arxiv.org)

VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models (arxiv.org)

Paradoxical noise preference in RNNs (arxiv.org)

Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics (arxiv.org)

Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning (arxiv.org)

MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (arxiv.org)

A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models (arxiv.org)

ELF: A Family of Encoder-Free ECG-Language Models (arxiv.org)

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition (arxiv.org)

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity (arxiv.org)

How Much Progress Has There Been in NVIDIA Datacenter GPUs? (arxiv.org)

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (arxiv.org)

Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training (arxiv.org)

Global Geometry Is Not Enough for Vision Representations (arxiv.org)

Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching (arxiv.org)

GottBERT: a pure German Language Model (arxiv.org)

Incentivized Collaboration in Active Learning (arxiv.org)

Discovering Nonlinear Static Relationships in Unlabeled Dataset using Autoencoder with Ordered Variance (arxiv.org)

Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees (arxiv.org)

Domain Adaptation with a Single Vision-Language Embedding (arxiv.org)

Efficient Hamiltonian, structure and trace distance learning of Gaussian states (arxiv.org)

Embedding-Space Diffusion for Zero-Shot Environmental Sound Classification (arxiv.org)

Mirror Descent Under Generalized Smoothness (arxiv.org)

GIFT: Geometry-Induced Functional Transfer for Category-level Object Manipulation (arxiv.org)

VDSB-GWSyn: Diffusion Schr\"{o}dinger Bridge for Controllable and Anatomically Feasible Guidewire Synthesis in Coronary Angiography (arxiv.org)

RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models (arxiv.org)

Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts (arxiv.org)

StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning (arxiv.org)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models (arxiv.org)

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say (arxiv.org)

GeoSAM-3D: Geodesic Prompt Propagation for Open-Vocabulary 3D Scene Segmentation from Monocular Video (arxiv.org)

TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version (arxiv.org)

Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics (arxiv.org)

EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction (arxiv.org)

Closing the Alignment-Maturity Gap in Federated Prototype Learning (arxiv.org)

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems (arxiv.org)

Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages (arxiv.org)

A Protocol-Language Model for Network Intrusion (Without Deep Packet Inspection) (arxiv.org)

A physics-informed foundation model for quantitative diffusion MRI (arxiv.org)

Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detection (arxiv.org)