AI.info
Latest Research — Page 78
Browse Latest Research on AI.info.
- DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion
- STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction
- Advancements in synthetic data extraction for industrial injection molding
- SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality
- LLMs are General Asynchronous Agents
- Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
- ST4VLA: Spatially Guided Training for Vision-Language-Action Models
- TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
- Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
- AfriNLLB: Efficient Translation Models for African Languages
- ConsistCompose: Unified Multimodal Layout Control for Image Composition
- Understanding Persuasion in Long-Running Agents
- SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
- Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
- Neural Induction of Finite-State Transducers
- FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders
- RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
- Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards
- Order-Only On-Policy Distillation
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
- Escaping the Filter Bubble: Evaluating Electroencephalographic Theta Band Synchronization as Indicator for Selective Exposure in Online News Reading
- WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms
- 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
- Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks
- LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
- TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series Data
- Maximizing the efficiency of human feedback in AI alignment: a comparative analysis
- C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression
- Action-Aligned Retrieval with Pairwise Multimodal Reranking for Text-Based Person Anomaly Search
- GENDIS: Gender-Related Discourse and Stance in Multilingual YouTube Comments from India, Kenya, and Nigeria
- OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
- Can Visual Generation Expand What Unified Multimodal Models Know?
- Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
- Automated Machine Learning in Radiomics: A Comparative Evaluation of Performance, Efficiency and Accessibility
- Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
- Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset
- On the Off-Policy Teacher in On-Policy Distillation
- SQuARE: Structured Query & Adaptive Retrieval Engine For Tabular Formats
- SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation