ReSyn: A Generalized Recursive Regular Expression Synthesis Framework Paper • 2603.24624 • Published 7 days ago • 4
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI Paper • 2606.18021 • Published 4 days ago • 1 • 2
Duration Aware Scheduling for ASR Serving Under Workload Drift Paper • 2603.11273 • Published Mar 11 • 2 • 3
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising Paper • 2606.20563 • Published 2 days ago • 17 • 2
No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages Paper • 2606.16827 • Published 5 days ago • 3
Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation Paper • 2606.16429 • Published 5 days ago • 2 • 5
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining Paper • 2606.20521 • Published 2 days ago • 5 • 2
When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? Paper • 2606.18531 • Published 4 days ago • 3 • 3
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks Paper • 2606.15872 • Published 6 days ago • 6 • 3
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows Paper • 2606.20404 • Published 2 days ago • 16 • 2
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages Paper • 2606.20517 • Published 2 days ago • 33 • 3
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 7 days ago • 63 • 4
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability Paper • 2606.19236 • Published 3 days ago • 8 • 4
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets Paper • 2606.13802 • Published 9 days ago • 1 • 3
LLM-Enabled NWDAF: A Step Toward AI-Native 6G Network Intelligence Paper • 2606.11877 • Published 10 days ago • 3
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish Paper • 2606.18717 • Published 3 days ago • 2 • 2
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning Paper • 2606.17682 • Published 4 days ago • 20 • 2