Uncovering the Limits of Proof Sharing for Neural Networks

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 incomplete verification techniques by reusing intermediate-layer abstract states, or templates, across queries. However, questions remain as to the robustness of template-based acceleration across varying network architectures, properties, datasets, and training methods. In this work, we perform a systematic study of the effectiveness of template-based acceleration and its limits. Our study shows that template subsumption rates can vary widely across scenarios. We present a novel metric of jointly stable neurons to explain this variation, showing that in some cases template-based techniques are very unlikely to provide any speedup. Then, we present FastCert, a novel technique for automatically distributing templates across neural network layers to increase performance impact, eschewing templates entirely if they are unlikely to produce a speedup. Across a large set of covering-design based $L_0$-verification tasks, FastCert achieved an average speedup of 1.13x over an extant template-based reuse technique.

PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

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 exhibit a tension between the GPU memory requirements of the model weights and the growing KV cache. We propose PagedWeight, a novel management method for MoE LLM serving that dynamically quantizes MoE model's weights at runtime and balances expert-weight precision with the KV cache sizes. PagedWeight exposes and effectively navigates the complex tradeoff between the model's task accuracy, memory consumption, and throughput/latency. Across several memory-sensitive MoE serving scenarios, PagedWeight improves the quality-memory tradeoff over several existing quantization baselines. PagedWeight achieves FP16-equivalent accuracy with up to 72.0% GPU memory savings and 1.94$\times$ throughput improvement, and improves quality over quantization methods by up to 39.3% at a similar memory budget with at most 4.1% throughput loss.

Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels

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 operators into efficient tiled GPU kernels. Nautilus's successive lowering design allows high-level optimizations, expression rewrites, and tile optimizations to be jointly applied in a single end-to-end system. Nautilus presents a novel auto-scheduler that discovers sequences of high-level optimizations, while preserving the regular program structure needed by tile optimizers. Nautilus's auto-scheduler captures complex interactions and trade-offs in the high-level optimizations, including aggressive global transformations like advanced reduction fusion. Nautilus is the first end-to-end tensor compiler capable of starting from a math-like description of attention and automatically discovering FlashAttention-3-like kernels, offloading the entire burden of optimization from the programmer to the compiler. Across five transformer-based models and 150 evaluation configurations on NVIDIA GH200 and RTX 5090 GPUs, Nautilus achieves up to 23% higher throughput than state-of-the-art compilers on GH200 and up to 42% on RTX 5090, while matching or exceeding manually written cuDNN kernels on many long-sequence configurations.

Enforcing Temporal Constraints for LLM Agents

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 ordering and sequencing of agent actions. For instance, agents may access sensitive data before authenticating users or process refunds to unauthorized payment methods, violations that require reasoning about sequences of action rather than an individual action. Existing guardrails rely on imprecise natural language instructions or post-hoc monitoring, and provide no formal guarantees that agents will satisfy temporal constraints. We present Agent-C, a novel framework that provides run-time guarantees ensuring LLM agents adhere to formal temporal safety properties. Agent-C introduces a domain-specific language for expressing temporal properties (e.g., authenticate before accessing data), translates specifications to first-order logic, and uses SMT solving to detect non-compliant agent actions during token generation. When the LLM attempts to generate a non-compliant tool call, Agent-C leverages constrained generation techniques to ensure that every action generated by the LLM complies with the specification, and to generate a compliant alternative to a non-compliant agent action. We evaluate Agent-C across two real-world applications: retail customer service and airline ticket reservation system, and multiple language models (open and closed-source). Our results demonstrate that Agent-C achieves perfect safety (100% conformance, 0% harm), while improving task utility compared to state-of-the-art guardrails and unrestricted agents. On SoTA closed-source models, Agent-C improves conformance (77.4% to 100% for Claude Sonnet 4.5 and 83.7% to 100% for GPT-5), while simultaneously increasing utility (71.8% to 75.2% and 66.1% to 70.6%, respectively), representing a new SoTA frontier for reliable agentic reasoning.

DINGO: Constrained Inference for Diffusion LLMs

Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffusion models lack the ability to provably enforce user-specified formal constraints, such as regular expressions, which makes them unreliable for tasks that require structured outputs, such as fixed-schema JSON generation. Unlike autoregressive models that generate tokens sequentially, diffusion LLMs predict a block of tokens in parallel. This parallelism makes traditional constrained decoding algorithms, which are designed for sequential token prediction, ineffective at preserving the true output distribution. To address this limitation, we propose DINGO, a dynamic programming-based constrained decoding strategy that is both efficient and provably distribution-preserving. DINGO enables sampling of output strings with the highest probability under the model's predicted distribution, while strictly satisfying any user-specified regular expression. On standard symbolic math and JSON generation benchmarks, DINGO achieves up to a 68 percentage point improvement over unconstrained inference

CRANE: Reasoning with constrained LLM generation

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 promising direction to enforce adherence to formal grammar, but prior works have empirically observed that strict enforcement of formal constraints often diminishes the reasoning capabilities of LLMs. In this work, we first provide a theoretical explanation for why constraining LLM outputs to very restrictive grammars that only allow syntactically valid final answers reduces the reasoning capabilities of the model. Second, we demonstrate that by augmenting the output grammar with carefully designed additional rules, it is always possible to preserve the reasoning capabilities of the LLM while ensuring syntactic and semantic correctness in its outputs. Building on these theoretical insights, we propose a reasoning-augmented constrained decoding algorithm, CRANE, which effectively balances the correctness of constrained generation with the flexibility of unconstrained generation. Experiments on multiple open-source LLMs and benchmarks show that CRANE significantly outperforms both state-of-the-art constrained decoding strategies and standard unconstrained decoding, showing up to 10% points accuracy improvement over baselines on challenging symbolic reasoning benchmarks GSM-symbolic and FOLIO.

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs

Mixed precision quantization has become an important technique for enabling the execution of deep neural networks (DNNs) on limited resource computing platforms. Traditional quantization methods have primarily concentrated on maintaining neural network accuracy, either ignoring the impact of quantization on the robustness of the network, or using only empirical techniques for improving robustness. In contrast, techniques for robustness certification, which can provide strong guarantees about the robustness of DNNs have not been used during quantization due to their high computation cost. This paper introduces ARQ, an innovative mixed-precision quantization method that not only preserves the clean accuracy of the smoothed classifiers but also maintains their certified robustness. ARQ uses reinforcement learning to find accurate and robust DNN quantization, while efficiently leveraging randomized smoothing, a popular class of statistical DNN verification algorithms, to guide the search process. We compare ARQ with multiple state-of-the-art quantization techniques on several DNN architectures commonly used in quantization studies: ResNet-20 on CIFAR-10, ResNet-50 on ImageNet, and MobileNetV2 on ImageNet. We demonstrate that ARQ consistently performs better than these baselines across all the benchmarks and the input perturbation levels. In many cases, the performance of ARQ quantized networks can reach that of the original DNN with floating-point weights, but with only 1.5% instructions.

IterGen: Iterative Structured LLM Generation

Large Language Models (LLMs) are widely used for tasks such as natural language and code generation. Still, their outputs often suffer from issues like privacy violations, and semantically inaccurate code generation. Current libraries for LLM generation rely on left-to-right decoding without systematic support for backtracking, limiting the ability to correct or refine outputs mid-generation. To address this issue, we introduce IterGen, an intuitive framework for iterative, grammar-guided LLM generation that enables users to move both forward and backward within the generated output based on grammar symbols. By leveraging a symbol-to-position mapping, IterGen ensures efficient and structured generation while allowing for corrections during the process. We demonstrate IterGen's effectiveness in two important applications: reducing privacy leakage in LLM outputs and improving the accuracy of LLM-generated SQL queries. Our code is available at https://github.com/uiuc-arc/itergen

Is Watermarking LLM-Generated Code Robust?

We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.

Improving LLM Code Generation with Grammar Augmentation

We present SynCode a novel framework for efficient and general syntactical decoding of code with large language models (LLMs). SynCode leverages the grammar of a programming language, utilizing an offline-constructed efficient lookup table called DFA mask store based on language grammar terminals. We demonstrate SynCode's soundness and completeness given the context-free grammar (CFG) of the programming language, presenting its ability to retain syntactically valid tokens while rejecting invalid ones. The framework seamlessly integrates with any language defined by CFG, as evidenced by experiments on CFGs for Python and Go. The results underscore the significant reduction of 96.07% of syntax errors achieved when SynCode is combined with state-of-the-art LLMs, showcasing its substantial impact on enhancing syntactical precision in code generation. Our code is available at https://github.com/uiuc-focal-lab/syncode.