AI.info

Latest Research — Page 71

Browse Latest Research on AI.info.

• SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?
• SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
• Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
• SeeDNorm: Self-Rescaled Dynamic Normalization
• ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models
• Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds
• TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
• Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
• GenRouter: Unified Workflow Routing for Agentic Image Generation
• Assessing LLM Reasoning Through Implicit Causal Chain Discovery in Climate Discourse
• When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
• Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
• Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
• Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
• An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems
• Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
• MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
• PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment
• OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graph
• Floor It, Then Fill It: Simulating Creator Ecosystems for Fair Video-Content Recommendation Systems at Billion User Scale
• Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis
• Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecture
• SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination
• HouseTour: A Virtual Real Estate A(I)gent
• On the Role of Hidden States of Modern Hopfield Network in Transformer
• GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
• Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texture
• Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale
• Spherical Leech Quantization for Visual Tokenization and Generation
• Automatic Field-of-View Adjustment for a View-Expansive Microscope via LSTM-Based Gaze and Pipette Motion Interpretation
• Towards Token-Level Text Anomaly Detection
• Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence
• VISTA: Verification In Sequential Turn-based Assessment
• BoundRL: Efficient Structured Text Segmentation through Reinforced Boundary Generation
• When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications
• Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
• Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated
• The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
• CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning