·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling1h◆Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL1h◆SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants1h◆No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions1h◆M\"OVE: A Holistic LLM Benchmark for the German Public Sector1h◆SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection1h◆Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization1h◆SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents1h◆Low-Latency Real-Time Audio Game Commentary System via LLM-Based Parallel Text Generation1h◆S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP1h◆Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data1h◆When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval1h◆EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments1h◆Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science1h◆Detecting Functional Memorization in Code Language Models1h◆Multi-Bitwidth Quantization for LLMs Using Additive Codebooks1h◆Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension1h◆Trait, Not State: The Durability of Reading Identity in Social Highlighting1h◆Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning1h◆Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents1h◆LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling1h◆Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL1h◆SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants1h◆No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions1h◆M\"OVE: A Holistic LLM Benchmark for the German Public Sector1h◆SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection1h◆Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization1h◆SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents1h◆Low-Latency Real-Time Audio Game Commentary System via LLM-Based Parallel Text Generation1h◆S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP1h◆Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data1h◆When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval1h◆EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments1h◆Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science1h◆Detecting Functional Memorization in Code Language Models1h◆Multi-Bitwidth Quantization for LLMs Using Additive Codebooks1h◆Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension1h◆Trait, Not State: The Durability of Reading Identity in Social Highlighting1h◆Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning1h◆Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents1h◆
News/SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
arxiv
PublishedMay 22, 2026 at 4:00 AM
—neutral

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.07711v2 Announce Type: replace Abstract: On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two models t

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivLoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling1harxivMulti-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL1harxivSkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants1harxivNo Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions1h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews