Actually there was some more to explore 😍🎉🎉
See you at the conference! @neuripsconf.bsky.social
#Neurips2026
@sfu-cs-ai.bsky.social
@sfu-cs-ai.bsky.socialActually there was some more to explore 😍🎉🎉
See you at the conference! @neuripsconf.bsky.social
#Neurips2026
@sfu-cs-ai.bsky.socialHappy to see these papers accepted #Neurips2026 🎊 🎊 🎊
Please come and find us at the conference!
More details & links in 🧵
@sydneycompsci.bsky.social🎉 Fariza Rashid, Van Duc Le, Rahat Masood, Gustavo Batista, Aruna Seneviratne, and Suranga Seneviratne's paper "ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation" was accepted at #NeurIPS2026!#timeseries #USyd
🔗 NeurIPS: neurips.cc/Conferences/...
@tfjmp.bsky.socialOur paper on learning transferable representations of OS entities from provenance graphs has been accepted at #NeurIPS2026!
Paper: tfjmp.org/publication...
Code: github.com/ubc-provena...
@jlhuili.bsky.socialOur paper DeepArrhythmia was accepted at #NeurIPS2026 🎉
Beat-level ECG arrhythmia detection labels every heartbeat in a recording. Most systems crop each beat and classify it in isolation, which throws away the rhythm.
@moritzwillig.bsky.socialAmazing work by @philosotim.bsky.social on Tracing Actual Causes accepted to #NeurIPS2026!
By exploiting the causal graph structure, we show how to efficiently enumerate all actual cause sets.
@athenaakrami.bsky.socialNow accepted at #NeurIPS2026 🎉
aab, ccd & eef share a pattern, regardless of the specific elements. How RNNs build abstract representations of sequence structure?
Led by Vezha Boboeva, who is on the faculty job market now. If you're hiring in comp/systems neuro, she's exactly who you want!
@philosotim.bsky.socialVery happy to share two new papers accepted at #NeurIPS2026! 🎉
In Tracing Actual Causes with Counterfactual Witness Maps, we present an algorithm for complete enumeration of actual causes in structural causal models.
@toniwuest.bsky.socialExcited to share that our paper ZendoWorld has been accepted to #NeurIPS2026! 🎉
ZendoWorld tests interactive visual reasoning and demonstrates that current agents (VLM and NeSy) still struggle with both rule induction and informative experimentation 🤖💭
@nandahkrishna.bsky.socialMOJO has been accepted to #NeurIPS2026! 🎉
We use SSL + unlabelled data for better decoding, stronger few-shot transfer, and more interpretable embeddings with POYO and POSSM (SoTA decoders for neural spikes).
Stay tuned for more results + torch_brain-based code! 👀
@curiousbiped.bsky.social🎉 Accepted at NeurIPS 2026: "M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals". Nested sinusoidal networks that never see the scan noise, with real-time sphere tracing. Video: 1% noise, input vs Instant-NGP vs ours. https://dsilvavinicius.github.io/m-plicits/ #NeurIPS2026
@alexwind.bsky.social“Benchmarking Sensor-Fault Robustness in Forecasting” was accepted at #NeurIPS2026 (Evaluations & Datasets) 🎉
Forecasters are usually tested on clean data. Here, sensor faults hit PatchTST's input, and its forecasts (blue) deviate from those on clean input (green). 1/8
@michaelyingyang.bsky.socialHappy to share three papers from my group accepted at NeurIPS 2026, spanning world model, multimodal scene understanding, and 3D perception.
Congratulations to all the students and collaborators!
#NeurIPS2026 #ComputerVision #MultimodalAI #WorldModels #SpatialIntelligence
@martinhebart.bsky.socialWhat is the nature of universal representations in AI models, and what determines whether they emerge?
Our paper accepted at #neurips2026 led by @florianmahner.bsky.social & @rothj.bsky.social addressed these questions comparing 162 vision models, with intriguing results.
arxiv.org/abs/2605.13675
🧵
@drlaschowski.bsky.social#NeurIPS2026 decisions are out. Congrats to those accepted. If yours wasn’t, keep going.
@oyaceliktutan.bsky.socialWhat a day yesterday. Receiving a sequence of 4 emails from @neuripsconf.bsky.social starting with “we are delighted to inform you..” Australia here we come! #neurips2026
@pseudomanifold.wsocial.euHappy to report that my lab has k #NeurIPS2026 publications. Since k is a large number, this means we are doing a good job and our science is great. Many even say it is _the best_ science. Thank you for your attention to this matter.
@pseudomanifold.topology.rocksHappy to report that my lab has k #NeurIPS2026 publications. Since k is a large number, this means we are doing a good job and our science is great. Many even say it is _the best_ science. Thank you for your attention to this matter.
@guillaumesalhagalvan.comOur work on two-level softmax sampling with Walid Bendada (Spotify) has been accepted at #NeurIPS2026! 🔥 Couldn't be happier! More details coming soon.
@trappmartin.eurosky.social