AI.info

Latest Research — Page 3

Browse Latest Research on AI.info.

• Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
• Disentangling Intrinsic Importance from Emergent Structure in Multi-Expert Orchestration
• Can Agentic Trading Systems Pay for Their Own Intelligence?
• Marathoner: Ultra-Long-Horizon Autonomous Intelligence
• Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
• CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
• VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
• Omni-RRM: Advancing Omni Reward Modeling via Automatic Rubric-Grounded Preference Synthesis
• ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions
• CalVLA: Shaping Native Confidence in Vision-Language-Action Policies with Outcome Supervision
• FORWARD: Dataset of a forwarder operating in rough terrain
• Automated Reproducibility Has a Problem Statement Problem
• Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
• How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method
• TerraMesh-Masks: Open-Vocabulary Segmentation for Earth Observation
• AppellateGen: A Benchmark for Appellate Legal Judgment Generation
• Fast and Scalable Score-Based Kernel Calibration Tests
• LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations
• Towards the Roof of the World: NLP Progress in Tibetan Languages
• Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
• EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
• Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
• ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering
• Fast Mining and Dynamic Time-to-Event Prediction over Multi-sensor Data Streams
• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization
• MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation
• From Rollouts to Recipes: Self-Contained Post-Training for LLMs
• Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio
• MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
• Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models
• MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data
• A Benchmark for Procedural Memory Retrieval in Language Agents
• Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
• What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies
• Neural Collapse in Test-Time Adaptation
• Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates
• Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification