AI News

SPADE: Sketch-guided Path Planning Augmented with Diffusion Experts (arxiv.org)

Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors (arxiv.org)

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents (arxiv.org)

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+ (arxiv.org)

Learning Power Flow with Confidence: A Probabilistic Guarantee Framework for Voltage Risk (arxiv.org)

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond (arxiv.org)

Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement (arxiv.org)

FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration (arxiv.org)

Causal Preference Elicitation (arxiv.org)

Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data Imputation (arxiv.org)

Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement (arxiv.org)

SAIL: Sound Abstract Interpreters with LLMs (arxiv.org)

Sample-Size Scaling of the African Languages NLI Evaluation (arxiv.org)

From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework (arxiv.org)

PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion (arxiv.org)

Self-Soupervision: Cooking Model Soups without Labels (arxiv.org)

PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios (arxiv.org)

TimeOmni-VL: Unified Models for Time Series Understanding and Generation (arxiv.org)

WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arxiv.org)

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation (arxiv.org)

When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming (arxiv.org)

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension (arxiv.org)

Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction (arxiv.org)

MemVerse: Multimodal Memory for Lifelong Learning Agents (arxiv.org)

A Cartesian-3j Framework for Machine Learning Interatomic Potentials (arxiv.org)

Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions (arxiv.org)

Training a Predictive Coding Network on ImageNet using Equilibrium Propagation (arxiv.org)

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics (arxiv.org)

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation (arxiv.org)

MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models (arxiv.org)

A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems (arxiv.org)

Inference Cost Attacks for Retrieval-Augmented Large Language Models (arxiv.org)

Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model (arxiv.org)

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs (arxiv.org)

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation (arxiv.org)

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization (arxiv.org)

Critical evaluation of PINN for FWD inverse analysis and differentiable FEM as an alternative (arxiv.org)

Bayesian Tensor Decomposition with Diffusion Model Prior (arxiv.org)

Resource-Constrained Adaptive Inference for Sequential Pricing (arxiv.org)

ScoreStop: Gradient-based early stopping using functional score tests (arxiv.org)

Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency (arxiv.org)

HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models (arxiv.org)

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models (arxiv.org)

FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data (arxiv.org)

Constitutional On-Policy Safe Distillation (arxiv.org)

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)

Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies (arxiv.org)

Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents (arxiv.org)

Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias (arxiv.org)