AI.info

Latest Research — Page 83

Browse Latest Research on AI.info.

• DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
• PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork
• Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
• WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition
• Learning Adaptive Parallel Execution for Efficient Code Localization
• Vista: Scene-Aware Optimization for Streaming Video Question Answering under Post-Hoc Queries
• HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognition
• Towards Authentic Movie Dubbing with Retrieve-Augmented Director-Actor Interaction Learning
• Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
• Dark3R: Learning Structure from Motion in the Dark
• DSLE: A Learning Environment for Dark Souls Boss Encounters
• EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
• Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
• OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations
• Artly: Exploring Digital Artists' Perceptions of AI-Generated Feedback
• Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation
• PlanU: Large Language Model Decision Making through Planning under Uncertainty
• Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection
• How can we assess human-agent interactions? Case studies in software agent design
• Protein Autoregressive Modeling via Multiscale Structure Generation
• Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation
• Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
• A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication
• TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts
• People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe
• Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI
• Simplifying Knowledge Transfer in Pretrained Models
• Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
• Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordination
• From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
• DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
• TACO: Temporal Consensus Optimization for Continual Neural Mapping
• Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
• PreferThinker: Reasoning-based Personalized Image Preference Assessment
• When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
• When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
• MoirfEolas and CríochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology
• Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
• EffGen: Enabling Small Language Models as Capable Autonomous Agents