AI.info
Latest Research — Page 59
Browse Latest Research on AI.info.
- VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
- KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
- Soft-Masked Diffusion Language Models
- Expressive Temporal Specifications for Reward Monitoring
- UETQuintet at BioCreative IX -- MedHopQA: Enhancing Biomedical QA with Selective Multi-hop Reasoning and Contextual Retrieval
- WSBD: Freezing-Based Optimizer for Quantum Neural Networks
- PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
- Better Capturing Interactions Between Products in~Retail: Revisited Negative Sampling for~Basket Choice Modeling
- FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning
- MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation
- CooperBench: Why Coding Agents Cannot be Your Teammates Yet
- Characterizing Agentic Flooding of Government Services
- SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
- E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
- MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models
- USS-Nav: Unified Spatio-Semantic Scene Graph for Lightweight UAV Zero-Shot Object Navigation
- Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
- Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering
- SciForma: Structure-Faithful Generation of Scientific Diagrams
- Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control
- LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
- DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
- IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
- Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 Astra
- GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions
- Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
- A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
- MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
- On the Convergence Rate of LoRA Gradient Descent
- Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
- AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
- RIDER: 3D RNA Inverse Design with Reinforcement Learning-Guided Diffusion
- Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
- Uncertain Pointer: Situated Feedforward Visualizations for Ambiguity-Aware AR Target Selection
- Online Optimization for Offline Safe Reinforcement Learning
- MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval
- Cliff: Learning Process Rewards from the First Mistake
- LAMP: Implicit Language Map for Robot Navigation
- Reinforcement Unlearning via Group Relative Policy Optimization
- Smaller Models, Better Rejects: Preference Distillation Scaling