AI.info

Latest Research — Page 121

Browse Latest Research on AI.info.

• CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology
• Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classification
• BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
• One Dimensional CNN ECG Mamba for Multilabel Abnormality Classification in 12 Lead ECG
• Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design
• Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean
• Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
• A Unified Moral-Value Dataset for Instruction Tuning
• Massively Multilingual Joint Segmentation and Glossing
• Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation
• On Improvisation and Open-Endedness: Insights for Experiential AI
• Bio-Inspired Palette Evolution in Indirectly Encoded Substrates: Timescale Compatibility Shapes Activation Function Discovery
• COS3D: Collaborative Open-Vocabulary 3D Segmentation
• Universal Diffusion-Based Probabilistic Downscaling
• CoD: A Diffusion Foundation Model for Image Compression
• Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
• Lumosaic: Hyperspectral Video via Active Illumination and Coded-Exposure Pixels
• LendNova: Towards Automated Credit Risk Assessment with Language Models
• Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
• On-Policy Delta Distillation
• Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction
• Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
• Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals
• Sparse auto-regressive modeling for scene generation from multi-view images
• Data and Learning Where it Matters for Contact-Rich Manipulation
• Toward a Time-Aware Assessment Framework for the Carbon Cost of AI-Enabled Decarbonization
• Alternative Fairness and Accuracy Optimization in Criminal Justice
• Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding
• Needle in the Web: A Benchmark for Retrieving Targeted Web Pages in the Wild
• N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs
• Efficient Estimation of Kernel Surrogate Models for Task Attribution
• Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration
• BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
• DEPO: Dual-Efficiency Preference Optimization for LLM Agents
• WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
• Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines
• Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume
• Geometric Robot Calibration Using a Calibration Plate
• What's the Catch? Evaluating Temporal Consistency in Vision-Language Models
• Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning