Reasoning AI news

Focuses on A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data.

Focuses on Agentic generation of verifiable rules for deterministic, self-expanding reaction classification.

Focuses on GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision.

Focuses on Understanding Large Language Models.

Focuses on Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution.

Focuses on Towards High-Resolution Visual Perception via Hierarchical Entity Exploration.

Focuses on SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive Inference.

Focuses on Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior.

Focuses on Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers.

Focuses on LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter.

Focuses on JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering.

Focuses on UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization.

Focuses on GEAR-Seg: A Grounded Explainable Agent for Reasoning Segmentation and Data Engine.

Focuses on HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking.

Focuses on MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos.

Focuses on Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy.

Focuses on Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models.

Focuses on Information-Regularized Attention for Visual-Centric Reasoning.

Focuses on AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration.

Focuses on From Detection to Action: Using LLM Agents for Fault-Tolerant Control.

Focuses on Localized Conformal Prediction for Image Classification with Vision-Language Models.

Focuses on MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs.

Focuses on MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations.

Focuses on Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models.

Focuses on See & Sniff: Learning Visuo-Olfactory Representations.

Focuses on How Good Can Linear Models Be for Time-Series Forecasting?.

Focuses on RSPC: A Benchmark for Modeling Stress and Psychiatric Conditions in Digitally Mediated Relationships using Psychiatrist Annotations.

Focuses on Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation.

Focuses on VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks.

Focuses on Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment.

Focuses on Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection.

Focuses on Offline Multi-agent Continual Cooperation via Skill Partition and Reuse.

Focuses on Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles.

Focuses on VisCritic: Visual State Comparison as Process Reward for GUI Agents.

Focuses on \textsc{DiARC}: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models.

Focuses on Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning.