TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation
arXiv:2606.29575v2 Announce Type: replace-cross Abstract: Recent advances in speech separation (SS) have led to compact front-end models with small parameter…
On the Convergence of Self-Improving Online LLM Alignment
arXiv:2606.31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the…
Improving multichannel speech enhancement through accurate room-acoustic simulations
arXiv:2606.31552v1 Announce Type: cross Abstract: Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
arXiv:2606.30560v2 Announce Type: replace-cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently…
What Drives Interactive Improvement from Feedback?
arXiv:2606.30774v1 Announce Type: new Abstract: We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone.…
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
arXiv:2606.27922v2 Announce Type: replace-cross Abstract: Current multimodal reflection mechanisms for long video understanding predominantly rely on closed-loop self-reflection within internal…
A Machine-Verified Proof of a Quantum-Optimization Conjecture
arXiv:2606.29687v1 Announce Type: cross Abstract: We report a machine-verified resolution of a problem open for over a decade in quantum…
Early Warning Signals for OpenVLA Failure under Visual Distribution Shift
arXiv:2606.29699v1 Announce Type: cross Abstract: Vision Language Action models combine perception, language grounding, and control in a single policy, but…
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
arXiv:2606.28153v2 Announce Type: replace-cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood. We provide evidence…
Recursive Self-Evolving Agents via Held-Out Selection
arXiv:2606.28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as…