AI.info

Latest Research — Page 2

Browse Latest Research on AI.info.

• Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation
• MeniMV: A Multi-view Benchmark for Meniscus Injury Severity Grading
• Does Learning Protein Folding Generalize to Broader Reasoning?
• V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
• Breaking the Static Assumption: A Dynamic-Aware LIO Framework Via Spatio-Temporal Normal Analysis
• SAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation
• iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data
• Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
• Investigating the Presence and Development of Student Instructor Preferences in a Large-Scale CS1 Course
• Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow Integration
• From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
• AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
• NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
• NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
• MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation
• VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift
• GHOST: Solving the Traveling Salesman Problem on Graphs of Convex Sets
• Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
• Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
• Decoupling Defense Strategies for Robust Image Watermarking
• MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration
• Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies
• Multi-Aspect Mining and Anomaly Detection for Heterogeneous Tensor Streams
• NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
• BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
• SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction
• Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
• Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
• Enhancing Capstone Program Workflow: A Case Study on a Platform for Managing Academic-Industry Projects
• TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
• Agent Plasticity: Measuring Self-Improvement Through Experience
• Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
• Political Advertising on Facebook During the 2022 Australian Federal Election: A Social Identity Perspective
• EnvLunch: The Environment as a Free Lunch for Learning to Interact
• EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants
• StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction
• SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
• Creating ConLangs to Probe the Metalinguistic Grammatical Knowledge of LLMs
• SynBullying: A Multi LLM Synthetic Conversational Dataset for Cyberbullying Detection
• Sketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation