67%Highly rated?Highly ratedVote to see the scoreNeurIPS 2026U Illinois ChicagoU Illinois at ChicagoIllinois Institute of TechnologyU WashingtonState University of New York at Agent benchmarks & environmentsJARVIS-Bench: Benchmarking Personal Intelligence Agents on Long-Horizon Real-User Daily TracesWeizhi Zhang, Wei-Chieh Huang, Yueqing Liang, Liwei Jiang and 36 moreAtlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026– ReadersNo votes yet2/20 AI panelreviewers recommend itReaders and the AI panel: vote on this paper to see what they said.Worth readingNot for meOnly vote on papers you've read. Sign in with GitHub to vote.AI panel: 2 of 20 reviewers recommend itlenient 2/5medium 0/10strict 0/5
78%Highly rated?Highly ratedVote to see the scoreNeurIPS 2026NorthwesternIllinois Institute of TechnologyU Michigan - Ann ArborU California, Los AngelesU California, San DiegoLong-context modelingAttention Sinks and Outliers in Attention ResidualsOASIS stabilizes dual-normalized attention-residual architectures via null routing and token-to-depth null coupling, reducing activation outliers by 81.75% and improving low-bit quantized reasoning by 42.11%.Haozheng Luo, Haoran Dai, Shaoyang Zhang, Xi Chen and 9 moreAtlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 3– ReadersNo votes yet11/20 AI panelreviewers recommend itReaders and the AI panel: vote on this paper to see what they said.Worth readingNot for meOnly vote on papers you've read. Sign in with GitHub to vote.AI panel: 11 of 20 reviewers recommend itlenient 1/5medium 8/10strict 2/5