AI.info
Latest Research — Page 4
Browse Latest Research on AI.info.
- HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench
- ARC Is a Vision Problem!
- BabyVision: Visual Reasoning Beyond Language
- UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
- ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
- Learning Interestingness in Automated Mathematical Theory Formation
- UniCon: A Unified System for Efficient Robot Learning Transfers
- Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents
- MCMoE: Completing Missing Modalities with Mixture of Experts for Incomplete Multimodal Action Quality Assessment
- T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
- JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
- Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
- C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction
- The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games
- Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
- Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving
- Budget-Constrained Step-Level Diffusion Caching
- PROGRESSLM: Towards Progress Reasoning in Vision-Language Models
- ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning
- TEAS: Trusted Educational AI Standard: A Framework for Verifiable, Stable, Auditable, and Pedagogically Sound Learning Systems
- SemanticBridge - A Dataset for 3D Semantic Segmentation of Bridges and Domain Gap Analysis
- QuantumBench: A Benchmark for Quantum Problem Solving
- Lattice-allocated Real-time Line Segment Feature Detection and Tracking Using Only an Event-based Camera
- Jag: Direct Box Prediction for Efficient Visual Grounding
- Semantic Radiance Fields as Simulators for Spatial Reasoning in Real-World Scenes
- Deceptron: Learned Local Inverses for Fast and Stable Physics Inversion
- AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding
- SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection
- DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
- BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
- Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
- How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
- Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods
- Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
- CGCE: Classifier-Guided Concept Erasure in Generative Models
- HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
- Rethinking Learning from Label Proportions via Moment Matching
- Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement
- SeLaR: Selective Latent Reasoning in Large Language Models
- LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models