Tracked topic
… I created a PR to add Flash Attention support for GPT-OSS: https://github.com/huggingface/transformers/pull/42345 If you can't wait for the PR to get merged and registered in PyPI, here's a patch: https://gist.github.com/markrogersjr/ebada9ad3a31381d8d4e0d956c852569
… Just another llm model with Long waited "ChatGPT" system prompt revealing openai/gpt-oss-20b with Mxfp4HfQuantizer on T4 : https://colab.research.google.com/drive/1Gsgdydt4KgTm3S Dbc Gz08S2mQG4G8X?usp=sharing more details: https://github.com/ai-bot-pro/achatbot/pull/179 GPT-OSS PACK ----- $0.00 For… …
… By grounding generation in physically meaningful density signals, EDMolGPT mitigates structural bias and produces molecules with 3D conformations . Evaluations on 101 biological targets verify the effectiveness. Our project page: https://jiahaochen1.github.io/EDMolGPT Page/. …
… You mention the fixes work for GPT-OSS-120B, but no experimental results are shown. …
… Our method is a heterogeneous ensemble of seven LLMs with two prompting variants , where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline gpt-oss-120b, 0.6390 . …
… GQKAE replaces the parameter-heavy feed-forward network components in GPT-style generative eigensolvers with hybrid quantum-inspired Kolmogorov-Arnold network modules , forming a compact HQKANsformer backbone. …
… Noted 🤗 gpt-5-nano is mapped to responses; I'll add the date alias but to use it directly specify responses.gpt-5-nano-2025-08-07 . …
… We report matched single-model sweeps of Claude Opus 4.7, Gemini 3.1 Pro, and GPT 5.5 on M1 Pro: in-distribution self-speedups span 1.00times to 10.7times. …
… Results on BrowseComp-Plus: Pi-Serini with GPT-5.5 achieves 83.1% answer accuracy and 94.7% surfaced evidence recall. …
… View arXiv page View PDF Add to collection Community SleepWalk introduces a scalable single-scene 3D benchmark that tests whether VLMs can translate natural-language instructions into continuous, collision-aware, interaction-compatible trajectories, revealing that current frontier models still fail… …