AI.info

Latest Research — Page 34

Browse Latest Research on AI.info.

• RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation
• Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network
• Image Generation as a Visual Planner for Robotic Manipulation
• Rethinking Deep Alignment Through The Lens Of Incomplete Learning
• DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting
• WaiT for the Signal: Simple Frequency-Aware Flow-Matching
• Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
• RadarGen: Automotive Radar Point Cloud Generation from Cameras
• Compositional Steering of Large Language Models with Steering Tokens
• 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
• Complexity as Advantage: A Regret-Based Perspective on Emergent Structure
• The Deleuzian Representation Hypothesis
• Text to Sketch Generation with Multi-Styles
• An Epistemic Perspective on Agent Awareness
• AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
• 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
• SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
• Depth-Supervised Fusion Network for Seamless-Free Image Stitching
• SARMAE: Masked Autoencoder for SAR Representation Learning
• Resurfacing Paralinguistic Awareness in Large Audio Language Models
• UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis
• Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM
• R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
• Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs
• Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning
• Text-Conditioned Background Generation for Editable Multi-Layer Documents
• Ontology-supported AI Model and Dataset Management
• DiffMM: Efficient Method for Accurate Noisy and Sparse Trajectory Map Matching via One Step Diffusion
• Think Twice: Branch-and-Rethink Reasoning Reward Model
• MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm
• WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation
• Length-MAX Tokenizer for Language Models
• Vision-Language Memory for Spatial Reasoning
• Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits