…View arXiv page View PDF Project page GitHub 59 Add to collection Community A unified framework for on-policy self-distillation This is an automated message from the Librarian Bot . I found…
…View arXiv page View PDF Project page GitHub 2 Add to collection Community Trained once on synthetic Boolean formulas, NRI induces interpretable DNF rules zero-shot on any tabular task. No retraining…
…page View PDF Project page GitHub 2 Add to collection Community Implicit Preference Alignment that removes the need for bad samples for preference optimization. This is an automated message from the Librarian…
…View arXiv page View PDF Project page GitHub 0 Add to collection Community We propose CPCANet, which unrolls CPCA into a differentiable network to learn a structured domain-invariant subspace for domain…
…View arXiv page View PDF Project page Add to collection Community Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi…
…View arXiv page View PDF Project page Add to collection Community Published in Engineering Science and Technology, an International Journal, 61 (2025), 101920 This is an automated message from the Librarian Bot…
…View arXiv page View PDF Project page GitHub 0 Add to collection Community How many domain experts can you stack before a VLM collapses? 🧱 GeoStack introduces a geometric framework to compose…
…D- RoPE aligns multi-layer semantics using dual-stream projection and multi-scale frequency signals, captures thread dependencies using tree-like distances , and alleviates the token-level Distance Dilution problem by incorporating…
…View arXiv page View PDF Project page Add to collection Community This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers…
…https://github.com/vita-epfl/EverAnimate Project page: https://everanimate.github.io/homepage/ Model and demo data: https://huggingface.co/epfl-vita/everanimate This is an automated message from the Librarian Bot…