AI.info

Latest Research — Page 81

Browse Latest Research on AI.info.

• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval
• AP-OOD: Attention Pooling for Out-of-Distribution Detection
• Distribution Matching Distillation Meets Reinforcement Learning
• Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation
• Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario
• Real-World Point Tracking with Verifier-Guided Pseudo-Labeling
• Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction
• Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives
• Temporal Slowness in Central Vision Drives Semantic Object Learning
• Generative Artificial Intelligence in Small and Medium Enterprises: Navigating its Promises and Challenges
• AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
• Towards Consistent Detection of Cognitive Distortions: LLM-Based Annotation and Dataset-Agnostic Evaluation
• FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
• Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck
• Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
• Pre to Post-Treatment Glioblastoma MRI Prediction using a Latent Diffusion Model
• Mixture of States: Routing Token-Level Dynamics for Multimodal Generation
• On the Fundamental Limits of LLMs at Scale
• Unleashing Perception-Time Scaling to Multimodal Reasoning Models
• Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow
• Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
• Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning
• 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
• On De-Individuated Neurons: Continuous Symmetries Enable Dynamic Topologies
• NVIDIA Nemotron 3: Efficient and Open Intelligence
• The Directed Prediction Change - Efficient and Trustworthy Fidelity Assessment for Local Feature Attribution Methods
• DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting
• WaiT for the Signal: Simple Frequency-Aware Flow-Matching
• When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications
• DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
• Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
• The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation
• RadarGen: Automotive Radar Point Cloud Generation from Cameras
• Review Based Entity Ranking using Fuzzy Logic Algorithmic Approach: Analysis
• LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
• Compositional Steering of Large Language Models with Steering Tokens
• FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning