Skip to content
Kempner Institute for the study of natural and artificial intelligence at Harvard University Kempner Institute Logo
  • About Us

    • About the Kempner
    • Kempner AI Cluster
    • Support the Kempner
  • People

    • Research Community
    • Institute Investigators
    • Associate Faculty
    • Research Fellows
    • Directory
  • Research

    • Our Research

      • Innovation in AI
      • Science of AI
      • AI and the Brain
    • Deeper Learning Blog
  • Resources

    • Open Science Resources
  • Programs

    • Kempner Research Fellowship
    • Graduate Fellowship
    • Post-Baccalaureate Program
    • Undergraduate Research Programs
  • Opportunities

    • Faculty Roles
    • Opportunities for Students, Grads & Staff
    • Kempner Institute Accelerator Awards
    • Moise Y. Safra Collaborative Research Award
  • Events

    • Calendar
    • Learning Dynamics in Natural and Artificial Intelligence
    • Kempner Seminar Series
    • Courses and Workshops
Calendar News Kempner Community
Harvard Shield
Kempner Institute for the study of natural and artificial intelligence at Harvard University Kempner Institute Logo Harvard Shield
  • About Us
    • About the Kempner
    • Kempner AI Cluster
    • Support the Kempner
  • People
    • Research Community
    • Institute Investigators
    • Associate Faculty
    • Research Fellows
    • Directory
  • Research
    • Our Research
      • Innovation in AI
      • Science of AI
      • AI and the Brain
    • Deeper Learning Blog
  • Resources
    • Open Science Resources
  • Programs
    • Kempner Research Fellowship
    • Graduate Fellowship
    • Post-Baccalaureate Program
    • Undergraduate Research Programs
  • Opportunities
    • Faculty Roles
    • Opportunities for Students, Grads & Staff
    • Kempner Institute Accelerator Awards
    • Moise Y. Safra Collaborative Research Award
  • Events
    • Calendar
    • Learning Dynamics in Natural and Artificial Intelligence
    • Kempner Seminar Series
    • Courses and Workshops
  • Calendar
  • News
  • Kempner Community
Kempner Institute Logo
Harvard University Logo

breadcrumb Menu

Back Link

Home Research Deeper Learning

Deeper Learning

A research blog from the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University.

Subscribe to RSS Feed

Feature Article

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

November 09, 2026
By: Jonathan Geuter and Subham Sahoo

Large language models generate text one token at a time, which makes inference slow. Diffusion language models generate many tokens in parallel, but they lose quality, and their speedups fade when a server handles many requests at once. We introduce Uno: a standard autoregressive (AR) model plus small diffusion weights that draft a block of tokens in one forward pass, while the unchanged AR weights check the draft. The output follows exactly the AR model's distribution. Uno is faster than leading speculative decoding methods at every batch size we tested, and can be built on top of existing open-weight models such as Qwen3-8B.

Blog List

2026

9 November 2026

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

By: Jonathan Geuter and Subham Sahoo

Large language models generate text one token at a time, which makes inference slow. Diffusion language models generate many tokens in parallel, but they lose quality, and their speedups fade when a server handles many requests at once. We introduce Uno: a standard autoregressive (AR) model plus small diffusion weights that draft a block of tokens in one forward pass, while the unchanged AR weights check the draft. The output follows exactly the AR model's distribution. Uno is faster than leading speculative decoding methods at every batch size we tested, and can be built on top of existing open-weight models such as Qwen3-8B.

  • Preprint
  • Code
  • Project page
6 November 2026

Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry

By: Jennifer Meng Lu, Ruochen Zhang, Isabelle Lee, David Alvarez-Melis, Ellie Pavlick, Naomi Saphra

Adversarial Concept Search (ACS) identifies meaningful conceptual scenarios that are likely to induce model failure without evaluating the model on specific inputs that instantiate those…

  • Preprint
  • Code
29 October 2026

Parametric Neural Control Differentiates Top Neural Network Models of Primate Visual Cortex

Hundreds of distinct models predict visual neural responses equally well. Are they all equally good models of visual neural tuning?

By: Jacob Prince*, Binxu Wang*, Thomas Fel, Akshay Jagadeesh, Parisa Vaziri, George Alvarez, Margaret Livingstone, and Talia Konkle

Leading AI models appeared to predict brain activity equally well, until asked to synthesize images that precisely control neural firing. Presented to monkeys during neural…

  • Preprint
  • Github
13 July 2026

Training Language Models That Can Continue to Learn

By: Tessa Han, Sebastian Bordt, Hanlin Zhang, and Sham Kakade

The usefulness of a pretrained model depends not only on what it has learned, but also on its plasticity, i.e., its ability to keep learning. However, despite its importance for downstream adaptation, model plasticity remains understudied in pretraining. The authors find that using stronger weight decay during pretraining improves model plasticity. Contrary to common practice, minimizing pretraining validation loss does not necessarily produce the most plastic model, i.e., the model that performs best after further training. The authors also find potential explanations for why weight decay improves plasticity, including more structured internal representations, simpler attention patterns, and reduced overfitting.

  • Paper
23 June 2026

Jailbreak Scaling Laws for Large Language Models: Polynomial–Exponential Crossover

By: Indranil Halder, Annesya Banerjee and Cengiz Pehlevan

The authors report that adversarial prompt-injection attacks on large language models can amplify attack success rate from the slow polynomial growth observed without injection to exponential growth with the number of inference-time samples.

  • Code
  • Preprint
27 April 2026

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments

By: Riley Simmons-Edler, Ryan Badman and Kanaka Rajan

Model-free RL agents trained on simple tasks can be evaluated by whether or not they achieve their simple rewards, but complex open-ended environments demand richer analysis. ForageWorld introduces a naturalistic foraging benchmark where agents must explore, remember food patches, and survive across procedurally generated arenas. In our experiments, naive RNN agents develop structured exploration strategies, multi-factor patch memory, and implicit future planning. These behaviors mirror those documented in foraging insects and rodents and are recoverable only using neuroscience-inspired analysis tools. The approach generalizes across arena sizes, transfers readily to other recurrent architectures, and opens a path toward behavioral and neural transparency in increasingly complex AI systems.

  • Code
  • Paper
16 March 2026

Energy-Based Fine-Tuning: Beyond Next-Token Prediction

By: Samy Jelassi*, Mujin Kwun*, Rosie Zhao*, Yuanzhi Li, Nicolo Fusi, Yilun Du, Sham M. Kakade and Carles Domingo-Enrich*

The authors introduce a Energy-Based Fine-Tuning (EBFT), a method that matches the long-range statistics of model generations to ground-truth sequences in high-dimensional feature spaces. EBFT corrects the error amplification caused by standard teacher-forced next token training while improving downstream task performance. Experiments show that EBFT matches the accuracy improvements of RLVR while requiring no external reward signal or verifier. In contrast to RLVR, EBFT simultaneously improves the validation cross-entropy.

  • Preprint
  • Project website
  • Code
9 March 2026

InputDSA: Demixing then comparing recurrent and externally driven dynamics in complex systems

By: Ann Huang and Kanaka Rajan

The authors introduce InputDSA, a new method to measure the similarity between two complex systems when they are driven by external inputs, like biological neural circuits or reinforcement learning agents. The method disentangles each systems’ intrinsic dynamics from its input-driven effects, enabling highly accurate, robust, and efficient comparisons of those components.

  • Preprint
  • Code
4 March 2026

Structure, Disorder, and Dynamics in Task-Trained Recurrent Neural Circuits

By: David Clark,* Blake Bordelon,* Jacob Zavatone-Veth,* Cengiz Pehlevan

The authors develop a mean-field theory of task-trained recurrent networks that continuously interpolates between these regimes, and find evidence that macaque motor cortex is best captured by an intermediate level of task-specific recurrent restructuring.

  • Paper
  • Code
  • Data
6 February 2026

Forecasting the Brain: Scalable Neural Prediction with POCO

By: Yu Duan and Kanaka Rajan

Predicting future neural activity is a critical step toward achieving real-time, closed-loop neurotechnologies. To this end, we introduce POCO, a unified forecasting model trained on…

  • Paper
  • Code
1 2 3 … 6 Next

Kempner Institute Harvard University Logo

Science and Engineering Complex (SEC)

150 Western Avenue
Allston, MA 02134
kempnerinstitute@harvard.edu

Social Media Links

X LinkedIn Github YouTube Hugging Face Bluesky Contact Us

Join Our Newsletter

Newsletter Signup

Footer Menu

Digital Accessibility Privacy Statement

© 2026 The President and Fellows of Harvard College

!