arXiv:2605. 01973v2 Announce Type: replace-cross Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2605. 01973v3 Announce Type: replace-cross Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes.
The paper introduces Training-Free Task Vectors (TFTVs), a method for computing task-vector-like directions in large language models without fine‑tuning. TFTVs map activation steering vectors to rank‑one weight‑space edits using only forward‑pass statistics, enabling arithmetic operations such as learning, forgetting, and composing edits. Experiments show that TFTVs consistently amplify, suppress, and combine target behaviors while preserving general knowledge, outperforming other editing and steering baselines.
arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.
arXiv:2606. 20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context.
arXiv:2608. 09507v1 Announce Type: cross Abstract: Natural language user preferences provide an interpretable interface for LLM personalization.
Learned optimization aims to improve upon hand-designed optimizers (e. g.