1 citations · 2 across the 14 of their papers we have counts for
16 papers
Conditional Flow Models Convert Epistemic Uncertainty into Apparent Aleatoric Variance
Navodita Sharma, Abhishek Shetty, Max Simchowitz +1
Conditional Flow Models (CFMs) are increasingly being used in place of deterministic predictors across machine learning, including for tasks that were classically formulated as reg…
H2LooP Telecom Model v1: From Telecom Comprehension to Autonomous Issue and PR Resolution
Amit Singh, Vedant Nipane, Mayank Goel +2
We present H2LooP Telecom Model v1, a domain-specialized large language models fine-tuned for the telecommunications industry. We release two domain-adapted model variants serving…
Dynamic Compression in Recurrent Networks
Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal
Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the s…
Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines
Jatin Kishnani, Mayank Goel, Amit Singh +2
We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for…
H2LooP Spark Preview: Continual Pretraining of Large Language Models for Low-Level Embedded Systems Code
Amit Singh, Vedant Nipane, Pulkit Agrawal +2
Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embed…
Training Language Models via Neural Cellular Automata
Dan Lee, Seungwook Han, Akarsh Kumar +1
Pre-training is crucial for large language models (LLMs), as it is when most representations and capabilities are acquired. However, natural language pre-training has problems: hig…
Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter +1
Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-pol…
RL's Razor: Why Online Reinforcement Learning Forgets Less
Idan Shenfeld, Jyothish Pari, Pulkit Agrawal
Comparison of fine-tuning models with reinforcement learning (RL) and supervised fine-tuning (SFT) reveals that, despite similar performance at a new task, RL preserves prior knowl…
Self-Adapting Language Models
Adam Zweiger, Jyothish Pari, Han Guo +3
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs…
Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning
Yi-Hsuan Hsiao, Wei-Tung Chen, Yun-Sheng Chang +2
Soft-actuated insect-scale micro aerial vehicles (IMAVs) pose unique challenges for designing robust and computationally efficient controllers. At the millimeter scale, fast robot…
Known Unknowns: Out-of-Distribution Property Prediction in Materials and Molecules
Nofit Segal, Aviv Netanyahu, Kevin P. Greenman +2
Discovery of high-performance materials and molecules requires identifying extremes with property values that fall outside the known distribution. Therefore, the ability to extrapo…
General Intelligence Requires Reward-based Pretraining
Seungwook Han, Jyothish Pari, Samuel J. Gershman +1
Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and rob…
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
Moritz Reuss, Jyothish Pari, Pulkit Agrawal +1
Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are bec…
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
Seungwook Han, Jinyeop Song, Jeff Gore +1
Autoregressive transformers exhibit adaptive learning through in-context learning (ICL), which begs the question of how. Prior works have shown that transformers represent the ICL…
Collective Model Intelligence Requires Compatible Specialization
Jyothish Pari, Samy Jelassi, Pulkit Agrawal
In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective…
Few-Shot Task Learning through Inverse Generative Modeling
Aviv Netanyahu, Yilun Du, Antonia Bronars +4
Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples. We refer to this problem as task concept learning a…