AI.info

Latest Research — Page 32

Browse Latest Research on AI.info.

• BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics
• Paradoxical noise preference in RNNs
• VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
• Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
• Phoneme- and Word-Level Metrics Using Self-Supervised Speech Representations for Forced Alignment Evaluation
• Instance-Level Composed Image Retrieval
• Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
• 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
• Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning
• DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection
• GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
• Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure
• AutoScape: Geometry-Consistent Long-Horizon Scene Generation
• What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
• Robust Sampling for Active Statistical Inference
• ForCM: Forest Cover Mapping from Multispectral Sentinel-2 Image by Integrating Deep Learning with Object-Based Image Analysis
• Rise of the Robochemist
• Hypothesis Testing for Generalized Thurstone Models
• ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing
• Advancements in synthetic data extraction for industrial injection molding
• Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
• ST4VLA: Spatially Guided Training for Vision-Language-Action Models
• Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
• ConsistCompose: Unified Multimodal Layout Control for Image Composition
• SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
• Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
• Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models
• Maximizing the efficiency of human feedback in AI alignment: a comparative analysis
• Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search
• OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
• Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
• Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset
• AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
• NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
• BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence
• FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution