AI.info

Latest Research — Page 28

Browse Latest Research on AI.info.

• Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
• DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
• FireRed-Image-Edit-1.0 Technical Report
• Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model
• A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance
• Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents
• Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping
• Unifying Masked Diffusion Models with Various Generation Orders and Beyond
• Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
• OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
• Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning
• Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory
• Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
• TrustResearcher: Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration
• Deep Learning-Based Early-Stage IR-Drop Estimation via CNN Surrogate Modeling
• Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
• ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
• Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting
• Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
• Functional Properties of the Focal-Entropy
• Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction
• T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning
• TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models
• Can LLMs Uncover Hidden Physical Laws through Free Exploration?
• Retrieval Sensitivity to Identity Signals in Queries
• Maximizing Efficiency of Dataset Compression for Machine Learning Potentials With Information Theory
• SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
• Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors
• Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light
• Embedding-Based Context-Aware Reranker
• Dynamic Algorithm for Explainable k-medians Clustering under lp Norm
• SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
• Is Newborn Wiring Special? Separating Wiring from Weight Placement in Connectome Reservoirs
• Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
• Relieving the Over-Aggregating Effect in Graph Transformers
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning
• UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
• ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
• Vela: User Behavior as Supervision Sparks LLM Intelligence
• Neural Green's Functions