AI.info

Latest Research — Page 120

Browse Latest Research on AI.info.

• Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Trading
• A Graph-Theoretical Perspective on Law Design for Multiagent Systems
• SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
• Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples
• SWE-IF: Aligning Code Evaluation with Human Preference
• Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
• QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
• Towards Scaling Laws for Symbolic Regression
• EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization
• ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting
• GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
• RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
• LM-mixup: Text Data Augmentation via Language Model based Mixup
• Georeferencing complex relative locality descriptions with large language models
• OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
• Emergence of Biased Consensus in Multi-Agent LLM Debates
• Solving Jigsaw Puzzles in the Wild: Human-Guided Reconstruction of Cultural Heritage Fragments
• Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision
• Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions
• SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
• PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions
• SUSD: Structured Unsupervised Skill Discovery through State Factorization
• Can Training Logs Make Model Comparisons More Precise?
• LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation
• Finite-Time Analysis of Gradient Descent for Shallow Transformers
• Remote Labor Index: Measuring AI Automation of Remote Work
• A System for Fast, Resilient, and Adaptable Loco-Manipulation Behaviors on Humanoid Robots
• Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos
• The Parameterized Complexity of Computing the VC-Dimension
• Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting
• Stop-RAG: Value-Based Retrieval Control for Iterative RAG
• A Sustainable AI Economy Needs Data Deals That Work for Generators
• SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
• One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography
• Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows
• Astra: General Interactive World Model with Autoregressive Denoising
• Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
• Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
• BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification
• Uncovering Strategic Egoism Behaviors in Large Language Models