AI.info

Latest Research — Page 33

Browse Latest Research on AI.info.

• In Quest of an Extensible Multi-Level Harm Taxonomy for Adversarial AI: Heart of Security, Ethical Risk Scoring and Resilience Analytics
• The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI Agents
• DCER: Dual-Stage Compression and Energy-Based Reconstruction
• Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
• Magpie: Real-Time World Renderer for Interactive Games
• DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry
• Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
• EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
• E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion
• Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
• ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games
• Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
• Once Upon an Input: Reasoning via Per-Instance Program Synthesis
• Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
• Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
• From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization
• Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
• SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
• Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models
• Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents
• Hazard-Responsive Digital Twin for Climate-Driven Urban Resilience and Equity
• SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
• Information-Theoretic Discrete Diffusion
• HazardAuditor: From Executable Threats to Safer Computer-Use Agents
• Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
• Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
• Separating Common and Unique Directions for Model Merging
• Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment
• Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions
• Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
• Large-Scale Biomedical RAG: Corpus Scaling, Document Representation, and Efficiency Trade-offs
• ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing
• MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretation
• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
• ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
• Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation
• HelloWorld: Enabling Socially Interactive Characters in Video World Models
• Membership Inference Test: Auditing Training Data in Object Classification Models
• Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation
• nanoMuse: An Open-Source Personal Agent for Every Device You Own