AI.info
Latest Research — Page 47
Browse Latest Research on AI.info.
- Meta$^n$: Recursive Self-Improvement through Emergent Depth
- Fairness Evaluation of Risk Estimation Models for Lung Cancer Screening
- RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
- MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
- DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
- MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
- Offline Reinforcement Learning with Generative Trajectory Policies
- Corpus-Based Approaches to Igbo Diacritic Restoration
- How Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline
- A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
- Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces
- GraphDecisionBench: Benchmarking System One Models on Graph Tasks
- Beyond Line-Level Filtering for the Pretraining Corpora of LLMs
- RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA
- Intrinsic Distribution Matching
- Emergence of Linear Truth Encodings in Language Models
- SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding
- Image Diffusion Preview with Consistency Solver
- PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks
- MUSE: Multi-Tenant Model Serving With Seamless Model Updates
- HeurekaBench: A Benchmarking Framework for AI Co-scientist
- MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction
- Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning
- HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time
- To Retrieve or To Think? Cross-Boundary Context Evolution for Multi-hop Complex Reasoning
- 4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
- AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
- Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
- EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset
- Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
- GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows
- Prescriptive tool for zero-emissions building fenestration design using hybrid metaheuristic algorithms
- AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction
- OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents Archive
- PUBG Ally: A Conversational Embodied Agent as an AI Teammate
- Estimation of Segmental Longitudinal Strain in Transesophageal Echocardiography by Deep Learning
- A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation
- JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction
- TraceForge: Distilling with Your Own Thinking
- Verified Critical Step Optimization for LLM Agents