SK
Sham Kakade
cs.LGstat.MLcs.AImath.OCcs.CLmath.STstat.THcs.CVcs.DScs.NA
On Valency
published · living versionsW_auee87mc·v1 · currentpublished
Preprints & journals
208 papers in the corpus · 2000–2026Unsupervised Multimodal Reward Modeling2610.12707v1 · Yueying Li, Jingxuan Fan, Kiant'e Brantley et al.2026 · 0 citationsarXiv
When Do Biological Reasoning Models Use Their Biological Inputs?2610.00898v1 · Ada Fang, Nikitha Thoduguli, Lukas Fesser et al.2026 · 0 citationsarXiv
Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems2609.38806v2 · Woosang Jeon, Jaeyeon Kim, Sham Kakade et al.2026 · 0 citationsarXiv
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models2607.26504v2 · Seunggeun Kim, Jaeyeon Kim, Taekyun Lee et al.2026 · 0 citationsarXiv
A Defense of the Quadratic Model2607.21716v1 · Alexandru Meterez, Pranav Ajit Nair, Depen Morwani et al.2026 · 0 citationsarXiv
Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods2606.19179v1 · Depen Morwani, Alexandru Meterez, Pranav Nair et al.2026 · 0 citationsarXiv
How Post-Training Shapes Biological Reasoning Models2606.16517v2 · Lukas Fesser, Hanlin Zhang, Michelle M. Li et al.2026 · 0 citationsarXiv
A Unifying View of Attention Sinks: From Mechanisms to Architectural Interventions2606.08105v2 · Lukas Fesser*, Mozes Jacobs*, Thomas Fel* et al.2026 · 0 citationsarXiv
RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training2606.04272v1 · Rachit Bansal, Clara Mohri, Tian Qin et al.2026 · 0 citationsarXiv
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions2606.02859v2 · Zhenting Qi, Huangyuan Su, Ao Qu et al.2026 · 0 citationsarXiv
Self-Improving Language Models with Bidirectional Evolutionary Search2605.28814v2 · Guowei Xu, Zhenting Qi, Huangyuan Su et al.2026 · 0 citationsarXiv
The Recurrent Transformer: Greater Effective Depth and Efficient Decoding2604.21215v1 · Costin-Andrei Oncescu, Depen Morwani, Samy Jelassi et al.2026 · 0 citationsarXiv
Evaluating Relational Reasoning in LLMs with REL2604.12176v2 · Lukas Fesser, Yasha Ektefaie, Ada Fang et al.2026 · 0 citationsarXiv
Peer-Predictive Self-Training for Language Model Reasoning2604.13356v3 · Shi Feng, Hanlin Zhang, Fan Nie et al.2026 · 0 citationsarXiv
Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models2603.12248v2 · Samy Jelassi, Mujin Kwun, Rosie Zhao et al.2026 · 0 citationsarXiv
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities2602.15327v2 · Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis et al.2026 · 0 citationsarXiv
Weight Decay Improves Language Model Plasticity2602.11137v2 · Tessa Han, Sebastian Bordt, Hanlin Zhang et al.2026 · 0 citationsarXiv
Next-token Preference: Scaling Unsupervised Reward Modeling2603.02225v3 · Jingxuan Fan, Yueying Li, Zhenting Qi et al.2026 · 0 citationsarXiv
Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training2602.10314v2 · Jaeyeon Kim, Jonathan Geuter, David Alvarez-Melis et al.2026 · 0 citationsarXiv
Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging2602.03702v2 · Alexandru Meterez, Pranav Ajit Nair, Depen Morwani et al.2026 · 0 citationsarXiv
GQ-VAE: A gated quantized VAE for learning variable length tokens2512.21913v1 · Theo Datta, Kayla Huang, Sham Kakade et al.2025 · 0 citationsarXiv
In Good GRACEs: Principled Teacher Selection for Knowledge Distillation2511.02833v3 · Abhishek Panigrahi, Bingbin Liu, Sadhika Malladi et al.2025 · 0 citationsarXiv
The Emergence of Complex Behavior in Large-Scale Ecological Environments2510.18221v3 · Joseph Bejjani, Chase Van Amburg, Chengrui Wang et al.2025 · 0 citationsarXiv
Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling2510.14717v2 · Alexandru Meterez, Depen Morwani, Jingfeng Wu et al.2025 · 0 citationsarXiv
Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise2510.13680v2 · Bingbin Liu, Rachit Bansal, Depen Morwani et al.2025 · 0 citationsarXiv
The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton2510.09378v2 · Natalie Abreu, Nikhil Vyas, Sham Kakade et al.2025 · 0 citationsarXiv
LOTION: Smoothing the Optimization Landscape for Quantized Training2510.08757v1 · Mujin Kwun, Depen Morwani, Chloe Huangyuan Su et al.2025 · 0 citationsarXiv
Selective Underfitting in Diffusion Models2510.01378v1 · Kiwhan Song, Jaeyeon Kim, Sitan Chen et al.2025 · 0 citationsarXiv
Fine-Tuning Masked Diffusion for Provable Self-Correction2510.01384v4 · Jaeyeon Kim, Seunggeun Kim, Taekyun Lee et al.2025 · 0 citationsarXiv
Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization2509.17251v2 · Jingfeng Wu, Peter L. Bartlett, Sham M. Kakade et al.2025 · 1 citationarXiv
Any-Order Flexible Length Masked Diffusion2509.01025v2 · Jaeyeon Kim, Lee Cheuk-Kit, Carles Domingo-Enrich et al.2025 · 0 citationsarXiv
Cognitive models can reveal interpretable value trade-offs in language models2506.20666v4 · Sonia K. Murthy, Rosie Zhao, Jennifer Hu et al.2025 · 0 citationsarXiv
Characterization and Mitigation of Training Instabilities in Microscaling Formats2506.20752v1 · Huangyuan Su, Mujin Kwun, Stephanie Gil et al.2025 · 0 citationsarXiv
EvoLM: In Search of Lost Language Model Training Dynamics2506.16029v2 · Zhenting Qi, Fan Nie, Alexandre Alahi et al.2025 · 0 citationsarXiv
A Simplified Analysis of SGD for Linear Regression with Weight Averaging2506.15535v1 · Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu et al.2025 · 0 citationsarXiv
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning2506.10378v1 · Jikai Jin, Vasilis Syrgkanis, Sham Kakade et al.2025 · 0 citationsarXiv
Interpreting the linear structure of vision-language model embedding spaces2504.11695v4 · Isabel Papadimitriou, Huangyuan Su, Thomas Fel et al.2025 · 0 citationsarXiv
Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining2504.07912v2 · Rosie Zhao, Alexandru Meterez, Sham Kakade et al.2025 · 0 citationsarXiv
Data-Efficient Multi-Agent Spatial Planning with LLMs2502.18822v1 · Huangyuan Su, Aaron Walsman, Daniel Garces et al.2025 · 0 citationsarXiv
The Role of Sparsity for Length Generalization in Transformers2502.16792v1 · Noah Golowich, Samy Jelassi, David Brandfonbrener et al.2025 · 0 citationsarXiv
Random Scaling of Emergent Capabilities2502.17356v5 · Rosie Zhao, Tian Qin, David Alvarez-Melis et al.2025 · 0 citationsarXiv
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions2502.06768v3 · Jaeyeon Kim, Kulin Shah, Vasilis Kontonis et al.2025 · 0 citationsarXiv
Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants2502.02431v1 · Depen Morwani, Nikhil Vyas, Hanlin Zhang et al.2025 · 0 citationsarXiv
Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives2501.05559v2 · Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle et al.2025 · 0 citationsarXiv
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos2412.07770v1 · Matthew Wallingford, Anand Bhattad, Aditya Kusupati et al.2024 · 3 citationsarXiv
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models2412.02674v2 · Yuda Song, Hanlin Zhang, Carson Eisenach et al.2024 · 5 citationsarXiv
Loss-to-Loss Prediction: Scaling Laws for All Datasets2411.12925v1 · David Brandfonbrener, Nikhil Anand, Nikhil Vyas et al.2024 · 0 citationsarXiv
How Does Critical Batch Size Scale in Pre-training?2410.21676v4 · Hanlin Zhang, Depen Morwani, Nikhil Vyas et al.2024 · 0 citationsarXiv
Mixture of Parrots: Experts improve memorization more than reasoning2410.19034v2 · Samy Jelassi, Clara Mohri, David Brandfonbrener et al.2024 · 1 citationarXiv
Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond2410.12982v2 · Costin-Andrei Oncescu, Sanket Purandare, Stratos Idreos et al.2024 · 0 citationsarXiv
Career total: 356 works. 208 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.