AI.info

Latest Research — Page 102

Browse Latest Research on AI.info.

• Are Large Reasoning Models Interruptible?
• SuperCLIP: CLIP with Simple Classification Supervision
• ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
• Beyond Egocentric Limits: Multi-View Depth-Based Learning for Robust Quadrupedal Locomotion
• StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
• OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
• Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
• Interpreto: An Explainability Library for Transformers
• Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
• Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
• Modular Expert Merging for Biomedical Retrieval
• COVR:Collaborative Optimization of VLMs and RL Agent for Visual-Based Control
• Is More Data Worth the Cost? Dataset Scaling Laws in a Tiny Attention-Only Decoder
• Exploring Reasoning Reward Model for Agents
• Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
• MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?
• PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories
• Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents
• A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization
• WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
• Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition
• AlterAtlas: Shifting Travel Planning from AI Generation to Validation via Persona-Driven Simulations
• UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
• CORE-T: COherent REtrieval of Tables for Text-to-SQL
• From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings
• Exploring LLMs for Scientific Information Extraction Using The SciEx Framework
• A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective
• MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
• Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
• BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields
• VENI: Variational Encoder for Natural Illumination
• GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
• Multi-Agent Deep Reinforcement Learning Under Constrained Communications
• Reasoning Up the Instruction Ladder for Controllable Language Models
• Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers
• Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models
• Order-Level Attention Similarity Across Language Models: A Latent Commonality
• You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
• Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
• Latent Variable Causal Discovery under Selection Bias