AI News

Inference-Time Projection for Physically Valid Biomolecular Diffusion Models (arxiv.org)

JIVEAdapter: A Multi-Task Additive Low-Rank Adapter via Joint and Individual Variation Explained (JIVE) (arxiv.org)

AttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVD (arxiv.org)

Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning (arxiv.org)

Event-Driven ML Pipeline Orchestration for Manufacturing: An AWS Industry Experience (arxiv.org)

Should We Skip Diffusion? (arxiv.org)

Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents (arxiv.org)

Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks (arxiv.org)

When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value (arxiv.org)

EPOCH: Reliable Discovery through Evidence-Governed Search (arxiv.org)

LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems (arxiv.org)

Learning When to Refine: Long-Horizon Reinforcement Learning for Budgeted Neural-Operator PDE Solvers (arxiv.org)

Comparative review of hybrid forecasting models for short-term prediction of building thermal load (arxiv.org)

Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks (arxiv.org)

When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO (arxiv.org)

TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning (arxiv.org)

From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models (arxiv.org)

Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction (arxiv.org)

Metonymic Circuits for Abstract Concept Grounding in Vision Transformers (arxiv.org)

RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway (arxiv.org)

FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving (arxiv.org)

Reinforcement Learning with Segment Reward Feedback under Linear Function Approximation (arxiv.org)

Ideal Paths for Approximating Logistic Gradient Descent Trajectories at Large Initialization (arxiv.org)

Best-of-$N$ Guidance for Test-time Diffusion Alignment (arxiv.org)

DePICT: Decision-Preserving Interface for Constrained Downstream Tasks (arxiv.org)

Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence (arxiv.org)

Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning (arxiv.org)

LionMuon: Alternating Spectral and Sign Descent for Efficient Training (arxiv.org)

ZonoGPT: Towards An Abstract Domain for Verifying Large GPT Models (arxiv.org)

KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems (arxiv.org)

PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction (arxiv.org)

SketchSSM: Write to the Full State, Read from a Compact Sketch (arxiv.org)

Adaptive Latent Capacity for World Models (arxiv.org)

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? (arxiv.org)

Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches (arxiv.org)

MiniScope: Authorizing Agents with Least-Privilege Permissions (arxiv.org)

Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane (arxiv.org)

A Neural JKO Scheme for Hellinger-Kantorovich Gradient Flows via Monge-Growth Pairs (arxiv.org)

The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies (arxiv.org)

BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation (arxiv.org)

Modeling Time-Dependent Responses of Optical Compressors with Selective State Space Models (arxiv.org)

TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts (arxiv.org)

Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes (arxiv.org)

TeleTune: Evolving Agent Skills From Offline Telemetry (arxiv.org)

Hypergraph-Enhanced Dual Convolutional Network for Bundle Recommendation (arxiv.org)

REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction (arxiv.org)

CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan? (arxiv.org)

Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings (arxiv.org)

MobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile Manipulation (arxiv.org)

Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security (arxiv.org)