AI.info
Latest Research — Page 25
Browse Latest Research on AI.info.
- Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
- BLiSS 1.0: Evaluating Bilingual Learner Competence in Second Language Small Language Models
- Synchronization of Multiple Videos
- SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
- DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization
- DiffFP: Learning Behaviors from Scratch via Diffusion-based Fictitious Play
- Text to Trust: Evaluating Fine-Tuning and LoRA Trade-offs in Language Models for Unfair Terms of Service Detection
- Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation
- Non-Asymptotic Analysis of Efficiency in Conformalized Regression
- FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem
- Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
- HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution
- Post-Training Fairness Control: A Single-Train Framework for Dynamic Fairness in Recommendation
- SimWorld-Robotics: Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration
- UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
- Litmus (Re)Agent: A Benchmark and Agentic System for Predictive Evaluation of Multilingual Models
- Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following
- Sparse Fine-Tuning for Parameter-Efficient Adversarial Training
- Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns
- ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs
- A Comprehensive Review of Bio-Inspired Approaches to Coordination, Communication, and System Architecture in Underwater Swarm Robotics
- Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
- Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation
- Towards Real-Time Fake News Detection under Evidence Scarcity
- Focus on What Really Matters in Low-Altitude Governance: A Management-Centric Multi-Modal Benchmark with Implicitly Coordinated Vision-Language Reasoning Framework
- Active Learning for Animal Re-Identification with Ambiguity-Aware Sampling
- mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud
- iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents
- Reward Learning through Ranking Mean Squared Error
- Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
- Offline Language-Based Support System for Tactical Decision-Making in Air Combat Operations
- GROVER: Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion
- SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling
- EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
- LAMP: Language-Assisted Motion Planning for Controllable Video Generation
- EventGPT: Next-Event Pretraining on Banking Customer Histories
- TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction
- Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
- How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
- Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer