36 citations · 79 across the 19 of their papers we have counts for
21 papers
Uncovering the Limits of Proof Sharing for Neural Networks
Kanak Das, Shubham Ugare, Bor-Yuh Evan Chang +3
Robustness verification of neural networks is increasingly important, due to their use in many critical domains. In certain scenarios, proof sharing has been shown to accelerate in…
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization
Yuchen Yang, Yifan Zhao, Anisha Dasgupta +1
Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy. However, in KV-cache-intensive serving scenarios, MoEs often exh…
Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels
Yifan Zhao, Yuchen Yang, Matei Budiu +1
We present Nautilus, a novel tensor compiler that moves toward fully automated math-to-kernel optimization. Nautilus compiles a high-level algebraic specification of tensor operato…
Enforcing Temporal Constraints for LLM Agents
Adharsh Kamath, Sishen Zhang, Calvin Xu +3
LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the or…
UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8
Preston Firestone, Shubham Ugare, Gagandeep Singh +1
Subword tokenization segments input text according to a pre-defined vocabulary to feed it into a language model; the language model, in turn, generates a sequence made from this sa…
Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs
Yifan Zhao, Egan Johnson, Prasanth Chatarasi +2
Operator fusion has become a key optimization for deep learning, which combines multiple deep learning operators to improve data reuse and reduce global memory transfers. However,…
RefineStat: Efficient Exploration for Probabilistic Program Synthesis
Madhav Kanda, Shubham Ugare, Sasa Misailovic
Probabilistic programming offers a powerful framework for modeling uncertainty, yet statistical model discovery in this domain entails navigating an immense search space under stri…
DINGO: Constrained Inference for Diffusion LLMs
Tarun Suresh, Debangshu Banerjee, Shubham Ugare +2
Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffus…
CRANE: Reasoning with constrained LLM generation
Debangshu Banerjee, Tarun Suresh, Shubham Ugare +2
Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a prom…
ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
Yuchen Yang, Yifan Zhao, Shubham Ugare +2
Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees…
IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
Shubham Ugare, Rohan Gumaste, Tarun Suresh +2
Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and in…
FastFlip: Compositional Error Injection Analysis
Keyur Joshi, Rahul Singh, Tommaso Bassetto +3
Instruction-level error injection analyses aim to find instructions where errors often lead to unacceptable outcomes like Silent Data Corruptions (SDCs). These analyses require sig…
Is The Watermarking Of LLM-Generated Code Robust?
Tarun Suresh, Shubham Ugare, Gagandeep Singh +1
We present the first in depth study on the robustness of existing watermarking techniques applied to code generated by large language models (LLMs). As LLMs increasingly contribute…
SynCode: LLM Generation with Grammar Augmentation
Shubham Ugare, Tarun Suresh, Hangoo Kang +2
LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components…
Incremental Randomized Smoothing Certification
Shubham Ugare, Tarun Suresh, Debangshu Banerjee +2
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method cons…
Incremental Verification of Neural Networks
Shubham Ugare, Debangshu Banerjee, Sasa Misailovic +1
Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set…
Mobiprox: Supporting Dynamic Approximate Computing on Mobiles
Matevž Fabjančič, Octavian Machidon, Hashim Sharif +3
Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input "difficulty", or user needs. The…
GAS: Generating Fast and Accurate Surrogate Models for Autonomous Vehicle Systems
Keyur Joshi, Chiao Hsieh, Sayan Mitra +1
Modern autonomous vehicle systems use complex perception and control components. These components can rapidly change during development of such systems, requiring constant re-testi…
Provable Defense Against Geometric Transformations
Rem Yang, Jacob Laurel, Sasa Misailovic +1
Geometric image transformations that arise in the real world, such as scaling and rotation, have been shown to easily deceive deep neural networks (DNNs). Hence, training DNNs to b…
Verifying Controllers with Convolutional Neural Network-based Perception: A Case for Intelligible, Safe, and Precise Abstractions
Chiao Hsieh, Keyur Joshi, Sasa Misailovic +1
Convolutional Neural Networks (CNN) for object detection, lane detection, and segmentation now sit at the head of most autonomy pipelines, and yet, their safety analysis remains an…
Exploiting Errors for Efficiency: A Survey from Circuits to Algorithms
Phillip Stanley-Marbell, Armin Alaghi, Michael Carbin +13
When a computational task tolerates a relaxation of its specification or when an algorithm tolerates the effects of noise in its execution, hardware, programming languages, and sys…