AI.info
Latest Research — Page 96
Browse Latest Research on AI.info.
- Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization
- SFTok: Bridging the Performance Gap in Discrete Tokenizers
- OpenStripe supports open-set identification and spatial stripe profiling in wild Amur tigers
- Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
- From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research
- Automated Design Optimization via Strategic Search with Large Language Models
- Implicit-Scale 3D Reconstruction for Multi-Food Volume Estimation from Monocular Images
- Tracking and Segmenting Anything in Any Modality
- WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
- Pairing-free Group-level Knowledge Distillation for Robust Gastrointestinal Lesion Classification in White-Light Endoscopy
- DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training
- Skill$^{\infty}$: Recursive Self-Improvement for Agent Skill Optimization
- Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis
- LLM-Mediated Demand Response Coordination in Smart Microgrids
- R$^2$Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
- Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
- TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
- Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
- MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)
- AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
- On Inherent Privacy of Posterior Sampling: A Unified Rényi-Divergence Framework
- Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
- NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
- AnyView: Synthesizing Any Novel View in Dynamic Scenes
- Uncovering Competency Gaps in Large Language Models and Their Benchmarks
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
- Beyond Detection: Exploring Evidence-based Multi-Agent Debate for Misinformation Intervention and Persuasion
- TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
- History-Aware Reasoning for GUI Agents
- Learning to Remove Lens Flare in Event Camera
- Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation
- Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods
- DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors
- Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers
- Federated Learning via Meta-Variational Dropout
- Foundations of Large Language Models
- Governing Well in the Algorithmic Age: The Foundations of Digital Statecraft
- Uncertainty Estimation by Flexible Evidential Deep Learning
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
- CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space