AI.info

Latest Research — Page 82

Browse Latest Research on AI.info.

• TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling
• MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
• Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices
• XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous Inputs
• Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
• When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• Complexity as Advantage: A Regret-Based Perspective on Emergent Structure
• Native Action-Prior Learning from Videos for World Action Models
• The Deleuzian Representation Hypothesis
• Learning Multimodal Embeddings with Evidence-Aligned Readout
• Text to Sketch Generation with Multi-Styles
• Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing
• An Epistemic Perspective on Agent Awareness
• AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
• APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
• Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
• Self-Refining Video Sampling
• Ovis-Image Technical Report
• ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects
• Falcon: A Comprehensive Chinese Text-to-SQL Benchmark for Enterprise-Grade Evaluation
• SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
• Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
• Depth-Supervised Fusion Network for Seamless-Free Image Stitching
• Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
• GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
• SARMAE: Masked Autoencoder for SAR Representation Learning
• Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
• Resurfacing Paralinguistic Awareness in Large Audio Language Models
• Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
• A Survey on Efficient Large Language Model Training: From Data-centric Perspectives
• UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis
• LastOPD: Taming Collapse in Latent On-Policy Distillation
• Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
• W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search
• Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning
• Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
• Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models
• Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM