AI.info

Latest Research — Page 64

Browse Latest Research on AI.info.

• JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers
• Efficient semantic uncertainty quantification in language models via diversity-steered sampling
• Progressive Learned Image Compression for Machine Perception
• UI-Venus-2 Technical Report
• Reflective Translation: Improving Low-Resource Machine Translation via Structured Self-Reflection
• EPRBench: A High-Quality Benchmark Dataset for Event Stream Based Visual Place Recognition
• On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
• CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
• FastJAM: a Fast Joint Alignment Model for Images
• Physiognomy Revisited: How Vision-Language Models Encode Sensitive Attributes Through Image Transformation
• CORGI: Efficient Pattern Matching With Quadratic Guarantees
• Disentangling Direction and Magnitude in Transformer Representations: A Double Dissociation Through L2-Matched Perturbation Analysis
• When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
• Function Words as Statistical Cues for Language Learning
• t-SNE Exaggerates Clusters, Provably
• Toward expert-level motivational interviewing for health behavior improvement with LLMs
• DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale
• OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
• Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
• Autoregressive Direct Preference Optimization
• Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Tasks
• Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
• ECSEL: Explainable Classification via Signomial Equation Learning
• Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG
• Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
• E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
• AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
• Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
• Inference-time Stochastic Refinement of GRU-Normalizing Flow for Real-time Video Motion Transfer
• Discrete Bayesian Sample Inference for Graph Generation
• Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity
• Robust Graph Condensation via Classification Complexity Mitigation
• Feature Recovery for Object Understanding After Irreversible Fire Damage
• Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
• InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
• Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion
• ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
• AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input/Output Design
• Dynamic Temperature Scheduler for Knowledge Distillation
• Pathology Context Recalibration Network for Ocular Disease Recognition