AI.info

Latest Research — Page 57

Browse Latest Research on AI.info.

• Qwen-Audio-3.1-ASR Technical Report
• FilmFlow: Agentic System for 3D Virtual Film Cinematography
• Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient
• GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models
• Technologies to Support Self-determination for People with Intellectual Disability and ASD
• $τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions
• PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems
• LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation
• The Physics Constraint Paradox: When Removing Explicit Constraints Improves Physics-Informed Data for Machine Learning
• SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection
• Unveiling the Heart-Brain Connection: An Analysis of ECG in Cognitive Performance
• Situation Graph Prediction for User Perspective Modeling
• BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
• REPAIR Approach for Social-based City Reconstruction Planning in case of natural disasters
• D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection
• Deriving Neural Scaling Laws from the statistics of natural language
• Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
• eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers
• Orbital Error Dynamics: Self-Organized Criticality, Ephemeral Parameter Resonance, and Non-Linear Biological Ontologies in Zero-Storage Neural Synthesis
• Thinking in 360°: Humanoid Visual Search in the Wild
• Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability
• Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge
• Reasoning-Aware Multimodal Fusion for Hateful Video Detection
• The persistence of painting styles
• DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning
• Algorithmic Gender Prediction Is Illegitimate, But Gender Imputation Can Yield Valid Measurements
• Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
• SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
• Every Weight Is a Path of Shared Discrete Decisions
• Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?
• CogRail: Benchmarking VLMs in Cognitive Intrusion Perception for Intelligent Railway Transportation Systems
• Structure from Collision via Hypothesis-Space Reasoning
• ALoDLM: Adaptively Looped Diffusion Language Models
• PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback
• BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
• LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
• SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning
• Robust Reward Machine Learning and Execution in Noisy Environments
• Latent Wasserstein Adversarial Imitation Learning