AI.info
Latest Research — Page 80
Browse Latest Research on AI.info.
- Code2Games: Enabling Coding Agents for Gaming World Generation
- DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior
- StopLoss: Teaching Agents to Predict Failure and Stop Early
- Formal Abductive Latent Explanations for Prototype-Based Networks
- Reward Modeling for Scientific Writing Evaluation
- Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image
- AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos
- Efficient Clustering with Provable Guardrails for LLM Inference at Scale
- CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
- ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
- Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards
- Event-Grounding Graph: Unified Spatio-Temporal Scene Graph from Robotic Observations
- X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning
- DAMBench: A Multi-Modal Benchmark for Deep Learning-based Atmospheric Data Assimilation
- Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
- MoralReason: Generalizable Moral Decision Alignment For LLM Agents Using Reasoning-Level Reinforcement Learning
- MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
- ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
- MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
- Bayesian Coreset Optimization for Personalized Federated Learning
- FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell
- Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
- A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
- Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
- Agentic Evaluation of Copyright Law Compliance
- Language-Independent Sentiment Labelling with Distant Supervision: A Case Study for English, Sepedi and Setswana
- ASAP: Visual Analytics for Identifying and Analyzing Image Patterns in AI-generated Images
- When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions
- Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation
- TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations
- AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding
- VMDT: Decoding the Trustworthiness of Video Foundation Models
- Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
- Terminal Velocity Matching
- NeurIPT: Foundation Model for Neural Interfaces
- Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
- ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges
- Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation
- OSWorld-Pro: Process-based Evaluation for Computer Use Agents
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models