AI.info
Latest Research — Page 72
Browse Latest Research on AI.info.
- From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
- Context-Adaptive Inference: A Unified Statistical and Foundation-Model View
- Optimal Transport under Group Fairness Constraints
- RAPTR: Radar-based 3D Pose Estimation using Transformer
- DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning
- Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation
- Continual Knowledge Adaptation for Reinforcement Learning
- From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
- MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization
- DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
- Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
- Automated urban waterlogging assessment and early warning through a mixture of foundation models
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models
- End-to-End Multi-Modal Diffusion Mamba
- MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
- MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
- FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
- Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
- Zero-Training Temporal Drift Detection for Transformer Sentiment Models: A Comprehensive Analysis on Authentic Social Media Streams
- Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
- Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
- FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction
- PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
- Extracting Dataset Mentions in Forced Displacement and FCV Documents: A Weakly Supervised Framework with LLM-Based Label Refinement
- Embodied Scene Rearrangement Planning
- Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
- Query-Guided Spatial-Temporal-Frequency Interaction for Music Audio-Visual Question Answering
- FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
- Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
- V-FiLLM: Verified Financial LLM Reasoning Benchmark
- ObjectTransforms for Uncertainty Quantification and Reduction in Vision-Based Perception for Autonomous Vehicles
- InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis
- Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
- NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
- Tensor Network Based Feature Learning Model
- Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment
- Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG
- Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
- HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
- Learning a Thousand Tasks in a Day