On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer
cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/zhenyi4/platour
Terminology
Sources
- Program Synthesis with Large Language Models
- KV-Lingo: Learning KV-Cache Translators with Distillation
- Evaluating Large Language Models Trained on Code
- See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
- When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Latent Space Communication via K-V Cache Alignment
- SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
- Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge
- Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- A Universal Context-Reuse Layer for Cross-Model KV Sharing
- CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff
- CacheBridge: Efficient Cross-Model KV Transfer for Multi-Model LLM Serving
- RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
- Qwen3 Technical Report
- OPRD: On-Policy Representation Distillation
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data