AI.info

Latest Research — Page 36

Browse Latest Research on AI.info.

• Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
• Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
• BrepLLM: Enabling Large Language Models to Understand Boundary Representations
• Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
• Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets
• Oracle-Efficient Combinatorial Semi-Bandits
• InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
• State World Models: Execute the Rules, Generate the Pixels
• Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data
• The information geometry of large language models is shared, learned, and controllable
• FreeInpaint: Tuning-free Prompt Alignment and Visual Rationality Enhancement in Image Inpainting
• Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
• TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
• Radiation-Preserving Selective Imaging for Pediatric Hip Dysplasia: A Cross-Modal Ultrasound-Xray Policy with Limited Labels
• GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
• Point-Supervised Facial Expression Spotting with Gaussian-Based Instance-Adaptive Intensity Modeling
• Closing the Modality Gap Aligns Group-Wise Semantics
• Sesame Plant Segmentation Dataset: A YOLO Formatted Annotated Dataset
• An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs
• Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
• BeetleFlow: An Integrative Deep Learning Pipeline for Beetle Image Processing
• MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents
• Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos
• Breaking the Adversarial Robustness-Performance Trade-off in Text Classification via Manifold Purification
• A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimization
• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation
• Virtual Head Attention
• ULME: Predictive Coupling for Mutually Reinforcing Embedding and Language Modeling
• What Layers When: Learning to Skip Compute in LLMs with Residual Gates
• From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?
• Doing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
• Patch-Derived or Register Tokens? Comparing Variable-Length Image Tokenizers
• PerfGuard: A Performance-Aware Agent for Visual Content Generation
• Future of AI Models: A Computational perspective on Model collapse
• Environment Evolution for Terminal Agents
• DiagramIR: An Automatic Pipeline for Educational Math Diagram Evaluation
• MoonBot: Modular and On-Demand Reconfigurable Robot Toward Moon Base Construction
• Exploiting Gradients in Bayesian Inference of Expensive Simulators
• Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs
• Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication