AI.info

Latest Research — Page 11

Browse Latest Research on AI.info.

• Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
• OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
• Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model
• RSI Arena: Towards Recursive Self-Improvement with Human Feedback
• Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
• Sample-Adaptivity Tradeoff in On-Demand Sampling
• EgoMaize: A First-Person Maize Instance Segmentation Benchmark under Severe Field Occlusion
• Don't Guess, Ask Wisely: Benchmarking and Training Proactive Elicitation in Open-Domain LLM Conversations
• Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal Retrieval
• Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era
• Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings
• Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
• MIBURI: Towards Expressive Interactive Gesture Synthesis
• Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment
• Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
• AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
• Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production
• AgentGarten: Code Worlds for Evolving Agents
• OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras
• cubic: CUDA-accelerated 3D Bioimage Computing
• Revisiting Orbital Minimization Method for Neural Operator Decomposition
• ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
• A Unified Definition of Hallucination: It's The World Model, Stupid!
• RuleSmith: Multi-Agent LLMs for Automated Game Balancing
• Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
• An Open-Access Benchmark of Statistical and Machine-Learning Anomaly Detection Methods for Battery Applications
• A Multi-fidelity Double-Delta Wing Dataset and Empirical Scaling Laws for GNN-based Aerodynamic Field Surrogate
• LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing
• Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
• Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
• SS-ESOAP: Self-Scaled Adaptive Preconditioning for Physics-Informed Learning
• NI-Tex: Non-isometric Image-based Garment Texture Generation
• DSBench: A Comprehensive Benchmark for Evaluating External and In-Cabin Risks
• Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games
• SpaceFlow: Locally Controllable 3D Generation
• RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
• Agentic schema-guided extraction of materials process knowledge from scientific literature
• KnowThyself: An Agentic Assistant for LLM Interpretability
• Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
• MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer