AI News

Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets (arxiv.org)

JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation (arxiv.org)

RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation (arxiv.org)

S-Space: Exploring Spatial Workspace in Multimodal Language Models (arxiv.org)

TernaryLLM: Ternarized Large Language Model (arxiv.org)

Constructive Bounds for the Topological Expressivity of Neural Networks (arxiv.org)

ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification (arxiv.org)

X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation (arxiv.org)

Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning (arxiv.org)

DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness (arxiv.org)

Graph World Models for Constrained Epidemic Policy Planning (arxiv.org)

MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution (arxiv.org)

Urban Power Grid Topology and Hierarchy Identification from Open Data (arxiv.org)

A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition (arxiv.org)

Harmonic analysis and circuit approximation of Sobolev functions on quantum input spaces (arxiv.org)

FACT: Fidelity-Aware Construction of Articulated Twins (arxiv.org)

Decoupling the Declarative from the Procedural in Vision-Language-Action Models (arxiv.org)

Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization (arxiv.org)

Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks (arxiv.org)

Recurrent Harness for Agentic Continual Learning (arxiv.org)

A Baseline Assessment for the Agentic Web Technology Stack (arxiv.org)

HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos (arxiv.org)

A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics (arxiv.org)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance (arxiv.org)

Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees (arxiv.org)

MetaJoin: Adaptive Join Selections for Heterogeneous Tables (arxiv.org)

Beyond Prediction-Set Size: Quantifying Conformal Uncertainty through Credal Geometry (arxiv.org)

Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning (arxiv.org)

LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation (arxiv.org)

VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models (arxiv.org)

PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs (arxiv.org)

Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution (arxiv.org)

Green-Routed Neural Operators: Physics Determines Where the Network Reads (arxiv.org)

Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos (arxiv.org)

AgroGround: Multi-Granularity Grounded Recognition in Agriculture (arxiv.org)

Solving VeriContest with a Lean-Backed Rust Verifier (arxiv.org)

GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive (arxiv.org)

Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents (arxiv.org)

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment (arxiv.org)

OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime (arxiv.org)

CoBe: A Benchmark For Conversational Counterfactual Text Editing (arxiv.org)

GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs (arxiv.org)

Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development (arxiv.org)

What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training (arxiv.org)

The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs (arxiv.org)

MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing (arxiv.org)

Rationally Linearized MLPs (arxiv.org)

Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data (arxiv.org)

Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models (arxiv.org)

FedPCD: Priority-Constrained Federated Aggregation (arxiv.org)