JS
Josh Susskind
cs.LGcs.CVcs.AIstat.MLcs.CLcs.ROFacial ExpressionAffectaffect-biased attentionamygdala
On Valency
published · living versionsW_3r3u6gpt·v1 · currentpublished
Weighted State Souping for Efficient Long-Context Retrieval
with William L. Tong, Aryo Lotfi, Emmanuel Abbe, Cengiz Pehlevan +1
1 version
Preprints & journals
56 papers in the corpus · 2007–2026Weighted State Souping for Efficient Long-Context Retrieval2610.25621v1 · William L. Tong, Aryo Lotfi, Emmanuel Abbe et al.2026 · 0 citationsarXivon Valency
Fewer Bits, More Tries: Recovering Capability Under Memory Constraints2610.15372v1 · Tomer Galanti, Josh Susskind, Eran Malach2026 · 0 citationsarXiv
How to Guide Your Language Flow2609.19356v1 · Rohit Dilip, Tianrong Chen, Yuyang Wang et al.2026 · 0 citationsarXiv
On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models2609.16540v1 · William L. Tong, Aryo Lotfi, Emmanuel Abbe et al.2026 · 0 citationsarXiv
Show Me Examples: Inferring Visual Concepts from Image Sets2607.02402v3 · Nick Stracke, Kolja Bauer, Stefan Andreas Baumann et al.2026 · 0 citationsarXiv
Normalizing Trajectory Models2605.08078v2 · Jiatao Gu, Tianrong Chen, Ying Shen et al.2026 · 0 citationsarXiv
Text-Conditional JEPA for Learning Semantically Rich Visual Representations2605.03245v1 · Chen Huang, Xianhang Li, Vimal Thilak et al.2026 · 0 citationsarXiv
Normalizing Flows with Iterative Denoising2604.20041v1 · Tianrong Chen, Jiatao Gu, David Berthelot et al.2026 · 0 citationsarXiv
Learning Long-term Motion Embeddings for Efficient Kinematics Generation2604.11737v1 · Nick Stracke, Kolja Bauer, Stefan Andreas Baumann et al.2026 · 0 citationsarXiv
The Coupling Within: Flow Matching via Distilled Normalizing Flows2603.09014v1 · David Berthelot, Tianrong Chen, Jiatao Gu et al.2026 · 0 citationsarXiv
The Design Space of Tri-Modal Masked Diffusion Models2602.21472v1 · Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec et al.2026 · 0 citationsarXiv
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows2511.20462v2 · Jiatao Gu, Ying Shen, Tianrong Chen et al.2025 · 0 citationsarXiv
Adapting Self-Supervised Representations as a Latent Space for Efficient Generation2510.14630v2 · Ming Gui, Johannes Schusterbauer, Timy Phan et al.2025 · 0 citationsarXiv
Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers2509.24317v1 · Xianhang Li, Chen Huang, Chun-Liang Li et al.2025 · 0 citationsarXiv
SimpleFold: Folding Proteins is Simpler than You Think2509.18480v4 · Yuyang Wang, Jiarui Lu, Navdeep Jaitly et al.2025 · 4 citationsarXiv
Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows2507.00425v1 · Ruixiang Zhang, Shuangfei Zhai, Jiatao Gu et al.2025 · 0 citationsarXiv
TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics2506.21757v2 · Tianrong Chen, Huangjie Zheng, David Berthelot et al.2025 · 0 citationsarXiv
STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis2506.06276v1 · Jiatao Gu, Tianrong Chen, David Berthelot et al.2025 · 2 citationsarXiv
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting2505.24088v1 · Chen Huang, Skyler Seto, Hadi Pouransari et al.2025 · 0 citationsarXiv
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models2501.12370v3 · Samira Abnar, Harshay Shah, Dan Busbridge et al.2025 · 0 citationsarXiv
3D Shape Tokenization via Latent Flow Matching2412.15618v3 · Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin et al.2024 · 0 citationsarXiv
Normalizing Flows are Capable Generative Models2412.06329v3 · Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran et al.2024 · 5 citationsarXiv
INRFlow: Flow Matching for INRs in Ambient Space2412.03791v2 · Yuyang Wang, Anurag Ranjan, Josh Susskind et al.2024 · 0 citationsarXiv
World-consistent Video Diffusion with Explicit 3D Modeling2412.01821v1 · Qihang Zhang, Shuangfei Zhai, Miguel Angel Bautista et al.2024 · 10 citationsarXiv
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models2411.02437v1 · Georgia Gabriela Sampaio, Ruixiang Zhang, Shuangfei Zhai et al.2024 · 0 citationsarXiv
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP2410.23698v1 · Chen Huang, Skyler Seto, Samira Abnar et al.2024 · 3 citationsarXiv
DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation2410.08159v2 · Jiatao Gu, Yuyang Wang, Yizhe Zhang et al.2024 · 0 citationsarXiv
On the benefits of pixel-based hierarchical policies for task generalization2407.19142v1 · Tudor Cristea-Platon, Bogdan Mazoure, Josh Susskind et al.2024 · 0 citationsarXiv
Improving GFlowNets for Text-to-Image Diffusion Alignment2406.00633v3 · Dinghuai Zhang, Yizhe Zhang, Jiatao Gu et al.2024 · 0 citationsarXiv
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling2405.21048v1 · Jiatao Gu, Ying Shen, Shuangfei Zhai et al.2024 · 2 citationsarXiv
How Far Are We from Intelligent Visual Deductive Reasoning?2403.04732v3 · Yizhe Zhang, He Bai, Ruixiang Zhang et al.2024 · 3 citationsarXiv
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization2401.15914v2 · Yuhang Zang, Hanlin Goh, Josh Susskind et al.2024 · 2 citationsarXiv
What Algorithms can Transformers Learn? A Study in Length Generalization2310.16028v1 · Hattie Zhou, Arwen Bradley, Etai Littwin et al.2023 · 10 citationsarXiv
Matryoshka Diffusion Models2310.15111v2 · Jiatao Gu, Shuangfei Zhai, Yizhe Zhang et al.2023 · 13 citationsarXiv
Adaptivity and Modularity for Efficient Generalization Over Task Complexity2310.08866v1 · Samira Abnar, Omid Saremi, Laurent Dinh et al.2023 · 0 citationsarXiv
Generative Modeling with Phase Stochastic Bridges2310.07805v4 · Tianrong Chen, Jiatao Gu, Laurent Dinh et al.2023 · 1 citationarXiv
Boolformer: Symbolic Regression of Logic Functions with Transformers2309.12207v2 · St'ephane d'Ascoli, Arthur Renard, Vassilis Papadopoulos et al.2023 · 1 citationarXiv
Value function estimation using conditional diffusion models for control2306.07290v1 · Bogdan Mazoure, Walter Talbott, Miguel Angel Bautista et al.2023 · 0 citationsarXiv
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping2306.05544v1 · Jiatao Gu, Shuangfei Zhai, Yizhe Zhang et al.2023 · 8 citationsarXiv
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images2304.06700v2 · Jiatao Gu, Qingzhe Gao, Shuangfei Zhai et al.2023 · 24 citationsarXiv
Stabilizing Transformer Training by Preventing Attention Entropy Collapse2303.06296v2 · Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin et al.2023 · 13 citationsIn International Conference on Machine Learning (pp. 40770-40803). PMLR. 2023
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors2303.03679v1 · Chen Huang, Hanlin Goh, Jiatao Gu et al.2023 · 3 citationsarXiv
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion2302.10109v1 · Jiatao Gu, Alex Trevithick, Kai-En Lin et al.2023 · 36 citationsarXiv
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation2210.04955v1 · Jiatao Gu, Shuangfei Zhai, Yizhe Zhang et al.2022 · 3 citationsarXiv
Efficient Representation Learning via Adaptive Context Pooling2207.01844v1 · Chen Huang, Walter Talbott, Navdeep Jaitly et al.2022 · 2 citationsarXiv
Learning Representation from Neural Fisher Kernel with Low-rank Approximation2202.01944v1 · Ruixiang Zhang, Shuangfei Zhai, Etai Littwin et al.2022 · 2 citationsarXiv
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models2112.01163v1 · Nitish Srivastava, Walter Talbott, Martin Bertran Lopez et al.2021 · 0 citationsarXiv
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics2104.10631v1 · Chen Huang, Shuangfei Zhai, Pengsheng Guo et al.2021 · 8 citationsarXiv
Set Distribution Networks: a Generative Model for Sets of Images2006.10705v1 · Shuangfei Zhai, Walter Talbott, Miguel Angel Bautista et al.2020 · 1 citationarXiv
Equivariant Neural Rendering2006.07630v2 · Emilien Dupont, Miguel Angel Bautista, Alex Colburn et al.2020 · 31 citationsarXiv
Career total: 61 works. 56 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.