Tracked topic
GitHub is a web-based platform for hosting and collaborating on software using Git version control, offering features such as pull requests.
…Our code is available at https://github.com/pat-jj/harness-1. View arXiv page View PDF GitHub 628 Add to collection Community 🔥 Introducing Harness-1 🔥 Harness-1 is a 20B open…
…reasonable time. The experimental code and links to the supplementary materials can be accessed through the GitHub repository: https://github.com/SibNN/SLM- RAG -EVAL. View arXiv page View PDF GitHub 2…
…Across image classification and language modeling benchmarks, FAAST matches or exceeds backprop-based adaptation while reducing adaptation time by over 90% and is competitive to memory/context-based adaptation while saving memory…
…Empirically, QGF outperforms prior test-time RL methods on single-task and goal-conditioned offline RL benchmarks with high-dimensional action spaces, and is competitive with state-of-the-art training-time…
…evolver , a harness tree with solve-time routing , and human-steering hooks for cases where history lacks the needed signal. Across prediction-market, security-competition, and event-forecasting streams, Adaptive Auto-Harness…
…decoding speed while maintaining competitive accuracy. AI-generated summary Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and discrete…
…Eros Fanì , Oğuzhan Ersoy Abstract A ridge regression-based routing method achieves competitive performance in selecting domain-expert LLMs for different tasks while enabling dynamic addition/removal of experts without retraining. Generated…
…observe 7 times faster encoding, 3.5 times faster decoding, and +8% ImageNet top-1 accuracy , while retaining compatibility with JPEG infrastructure. Our code is available at https://github.com/UT-SysML…
…competitive with state-of-the-art methods across distinct tasks and generalize robustly to in-the-wild scenarios, even when trained on fewer than 1,000 videos. Project page: https://houyuanchen111.github…
…Our experimental results show that SWM significantly outperforms time-series foundation models, achieving state-of-the-art results on Kalshi data and demonstrating competitive performance on Polymarket data, while offering interpretable insights…