Search results for #NeurIPS2023
🌟 New AI Paper 🌟 👏 Kudos to Shang and team for their groundbreaking work: "Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Grace and team for their groundbreaking work: "Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Yangqing and team for their groundbreaking work: "Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Zhenxing and team for their groundbreaking work: "Efficient Subgame Refinement for Extensive-form Games" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Li-wei and team for their groundbreaking work: "VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Ming-Kun and team for their groundbreaking work: "Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Antoine and team for their groundbreaking work: "RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
Can't wait for #ICLR2024? Check out the new @ClimateChangeAI blog post - our recap of our #NeurIPS2023 workshop, including summaries of the best papers. Read the full post here 👇climatechange.ai/blog/2024-04-1…
🌟 New AI Paper 🌟 👏 Kudos to Christopher and team for their groundbreaking work: "(Amplified) Banded Matrix Factorization: A unified approach to private training" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/6…
🌟 New AI Paper 🌟 👏 Kudos to Anders and team for their groundbreaking work: "Constant Approximation for Individual Preference Stable Clustering" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Qitao and team for their groundbreaking work: "A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Taira and team for their groundbreaking work: "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
🌟 New AI Paper 🌟 👏 Kudos to Moritz and team for their groundbreaking work: "Do Not Marginalize Mechanisms, Rather Consolidate!" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
TMLR @TmlrOrg 2023 #'s: -2098 reviewers -202 action editors -~550 published papers -~100 submissions/month -acceptance rate: ~50% (66% if ignoring desk rejections & withdrawls) -Median days to decision for conference-length papers: 91.4 (vs 127 for #NeurIPS2023, > 200 JMLR) 2/n
We are glad to share our last #LatinXinAI workshop at #NeurIPS2023 in New Orleans! Check out the insightful discussions, keynotes, and presentations from top experts in the field. 🔎Don't miss out on this valuable resource Watch the full playlist here: buff.ly/3U5lpsR 👀
🌟 New AI Paper 🌟 👏 Kudos to Mintong and team for their groundbreaking work: "DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
Training AI agents from human feedback is critical for safety and alignment. To aid this, we developed two related datasets for Minecraft! 💎 📝 Read our #NeurIPS2023 Datasets & Benchmarks Oral paper: arxiv.org/abs/2312.02405 🧑💻 Data & code: github.com/minerllabs/bas… 🧵 1/n
🌟 New AI Paper 🌟 👏 Kudos to Jacob and team for their groundbreaking work: "Learning Curves for Deep Structured Gaussian Feature Models" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…
@Michael_J_Black Shameless plug: At #NeurIPS2023, we showed that StyleGAN ‘knows’ intrinsic images as defined by Barrow & Tenenbaum. We then introduced a general method, intrinsic-LoRA, for extracting these intrinsics from any generative model; we also compare to DINO-v2. intrinsic-lora.github.io
@Michael_J_Black Shameless plug: At #NeurIPS2023, we showed that StyleGAN ‘knows’ intrinsic images as defined by Barrow & Tenenbaum. We then introduced a general method, intrinsic-LoRA, for extracting these intrinsics from any generative model; we also compare to DINO-v2. intrinsic-lora.github.io
🌟 New AI Paper 🌟 👏 Kudos to Agustinus and team for their groundbreaking work: "The Geometry of Neural Nets' Parameter Spaces Under Reparametrization" 📅 Presented at #NeurIPS2023! bytez.com/read/neurips/7…