Consistency Training Can Entrench Misalignment
arXiv:2606.03810v2 Announce Type: replace-cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.…
Explicit dynamic cross-strand interactions for DNA sequence language modelling
Nature Machine Intelligence, Published online: 04 June 2026; doi:10.1038/s42256-026-01249-1 Yang et al. developed CrossDNA, a parameter-efficient language model for cross-strand…
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
arXiv:2606.00395v2 Announce Type: replace-cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement…
Visual Graph Scaffolds for Structural Reasoning in Large Language Models
arXiv:2606.02673v1 Announce Type: new Abstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as…
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
arXiv:2606.02240v2 Announce Type: replace-cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from…
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
arXiv:2606.03504v1 Announce Type: cross Abstract: We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language…
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
arXiv:2606.03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle…
MOSS-Audio Technical Report
arXiv:2606.01802v2 Announce Type: replace-cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio…