AI.info

Latest Research — Page 76

Browse Latest Research on AI.info.

• Warm-Starting Iterative Gaussian Processes for Faster Sequential Inference
• DART: A Structured Dataset of Regulatory Drug Documents in Italian for Clinical NLP
• EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
• RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
• Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
• Self-Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation
• FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation
• Modal Logic Neural Networks
• Scaling Properties of Same-Family On-Policy Distillation
• BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
• EEG-X: Device-Agnostic and Noise-Robust Foundation Model for EEG
• AV-Dialog: Spoken Dialogue Models with Audio-Visual Input
• Paradoxical noise preference in RNNs
• Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation
• SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image
• VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
• Mosaic: Multi-Session Agentic Reinforcement Learning
• Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
• SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
• Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation
• From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
• DiscoverDCP: A Data-Driven Approach for Construction of Disciplined Convex Programs via Symbolic Regression
• NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
• Instance-Level Composed Image Retrieval
• Encoding and Understanding Astrophysical Information in Large Language Model-Generated Summaries
• Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
• Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents
• A Second-Order Attention Mechanism For Prostate Cancer Segmentation and Detection in Bi-Parametric MRI
• DIJIT: A Robotic Head for an Active Observer
• Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization
• Learning Skill-Attributes for Transferable Assessment in Video
• Entropy Aware Reward Guidance for Diffusion Language Model Alignment
• Learnable Low-Rank Polynomial Sketch for Effective Linear Attention
• Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
• Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
• IonCast: A Deep Learning Framework for Forecasting Ionospheric Dynamics
• Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes
• Remember Me, Not Save Me: A Collective Memory System for Evolving Virtual Identities in Augmented Reality
• Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads
• The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation