Searcharxiv⌕ Search

arXiv subjects

Vijay Janapa Reddi

Publications and source records attributed to Vijay Janapa Reddi.

At least 19 recordsLinked to original sources
arXiv2026

Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often focus on components other than the inference engine itself (e.g., network proxies or code execution environments). However, the inference engine is an attractive target for a misaligned model. For example, if a model can trigger exploits in that engine merely by generating specially-crafted output tokens, the model can initiate a multi-step, to-the-bare-metal exploit chain in the engine, without relying on vulnerabilities in other components of the inference stack, and without assistance from externally-provided, maliciously-crafted input tokens. In this paper, we show that a misaligned model can perform inference engine fingerprinting to determine the specific engine (e.g., vLLM, SGLang) which executes the model. Once the engine has been fingerprinted, the model can leverage engine-specific exploits to take control of the engine using only carefully-selected output tokens. We provide concrete examples of model fingerprints in five popular engines, and demonstrate how realistic agentic harnesses allow a model to leverage those fingerprints to identify the local engine. We also describe a proof-of-concept, to-the-bare-metal exploit chain that originates from a fingerprinted (and subsequently compromised) inference engine. We conclude by discussing several ways that inference engines could be changed to make fingerprinting attacks more difficult.

cs.CR↗
arXiv2026

Rethinking Heterogeneous System Disaggregation for Subquadratic Attention

Frontier language models are more aggressively using subquadratic attention to reduce the memory footprint and compute requirements during inference while still delivering frontier accuracy. While existing systems make dense attention-centric disaggregated serving decisions, we show that disaggregating inference around the unique arithmetic intensity and memory footprint of subquadratic attention LLMs can achieve significant throughput and energy efficiency gains on emerging DRAM-based and SRAM-only heterogeneous systems. We introduce SQD (SubQuadratic Disaggregation), a fine-grained heterogeneous disaggregation scheme that splits decode by quadratic and subquadratic attention rather than by operator type, and that applies across subquadratic attention variants. For sparse attention LLMs, we disaggregate decode into top-k selection, which must index through the full KV, and top-k attention plus FFN, which have static memory footprints. For linear and sliding-window attention LLMs, we disaggregate decode into dense attention layers and subquadratic attention layers plus FFN. In an adjusted 8xB200 heterogeneous system proxy, we observe average tokens/J improvements of 53% on GLM 5.2, 31% on Nemotron 3 Ultra, and 56% on Gemma 4 31B over the strongest GPU-only baselines. In an analytical model of a Rubin plus LPX system with fixed power budgets, we observe 1.2x to 1.5x tighter achievable latencies and up to 3.6x higher throughput over the best baseline of attention-FFN disaggregation. Our experiments also reveal architectural insights on chip and interconnect provisioning for next-generation heterogeneous systems serving subquadratic attention.

cs.AI↗
arXiv2026

Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems

Affective computing has advanced wearable state inference, but on-device reasoning about whether, when, and how to intervene remains challenging. We present Affective Agent, a three-layer reference architecture for personalized intervention reasoning under uncertainty on wearable-class hardware. It combines a compact sub-billion-parameter language model with physiological evidence, context, and user history to decide whether, when, and how to intervene, without cloud dependency or per-user retraining. The architecture is organized into three interacting layers (perception, personalization, and reasoning), adapting to individual users through host-managed structured memory evolution rather than per-user weight updates. We instantiate Affective Agent in indoor environmental quality control and evaluate it on held-out, simulator-generated longitudinal scenarios spanning physiological variation, context, signal quality, and intervention history. Results show that memory-driven personalization and two-pass structured reasoning improve intervention decisions within this synthetic evaluation. By moving the decision layer on-device, this work demonstrates a path from wearable state inference toward closed-loop, personalized intervention on wearable-class hardware.

cs.AI↗
arXiv2026

QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture

The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from current large language model (LLM) evaluations. To this end, we present QuArch (pronounced 'quark'), the first benchmark designed to facilitate the development and evaluation of LLM knowledge and reasoning capabilities specifically in computer architecture. QuArch v1.0 provides a comprehensive collection of 2,671 expert-validated question-answer (QA) pairs covering various aspects of computer architecture, including processor design, memory systems, and interconnection networks. Our evaluation reveals that while frontier models possess domain-specific knowledge, they struggle with skills that require higher-order thinking in computer architecture. Frontier model accuracies vary widely (from 34% to 73%) on these advanced questions, highlighting persistent gaps in architectural reasoning across analysis, design, and implementation QAs. Furthermore, via fine-tuning we find that QuArch can translate to improved performance on a realistic memory hierarchy design task, resulting in up to 1.99x more area-efficient solutions and up to 40% more viable solutions overall. By holistically assessing fundamental skills, QuArch provides a foundation for building and measuring LLM capabilities that can accelerate innovation in computing systems. The QuArch benchmark and leaderboard are publicly available at: https://quarch.ai/.

cs.AR↗
arXiv2026

ArchEval: Measuring AI Agents as Computer Architects

Computer architecture has long used benchmarks to make progress measurable. LLM agents create a different measurement problem: success is not merely writing code or tuning parameters. The agent must interpret workloads, choose mechanisms, use simulators, predict performance, satisfy hard constraints, and decide which feasible design is worth evaluating. This paper introduces ArchEval, a benchmark and platform for evaluating LLM agents on computer architecture design and optimization. It contains 20 challenges across CPU core mechanisms, system architecture, memory systems, accelerators, and compute-in-memory, backed by eight simulators. Each challenge is posed under three settings: L1 full harness, with repeated simulator feedback; L2 simulator-code container, where simulator source is available but the agent must assemble its own workflow; and L3 agent-only, with no runnable feedback before submission. Each run reports baseline-normalized verifier performance and records the full trajectory, connecting results to workload analysis, simulator-tool use, prediction, constraint handling, and artifact integrity. Initial results show a sharp boundary in current agents. With L1 support, all four evaluated agents reach or exceed baseline and improve real designs across diverse simulators. Removing support exposes weaknesses: many agents fail to turn simulator source into useful experiments, and L3 predictions often disagree with verifier results. In L3, only GPT-5.5 + Codex remains above baseline, reaching 1.21x geomean performance and a 65% win rate; the other three fall below baseline. Even GPT-5.5 + Codex has only a 15% performance-modeling pass rate. ArchEval frames today's agents as useful optimization assistants rather than autonomous architects, and identifies capabilities needed next: simulator-tool use, calibrated prediction, pre-feedback judgment, and useful mechanism discovery.

cs.AR↗
arXiv2026

MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems

As machine learning shifts from laboratory curiosity to critical infrastructure, the systems that sustain it span an extraordinary range, from sub-milliwatt microcontrollers to multi-gigawatt datacenter fleets. Reasoning across this range is hard: empirical profiling requires the target hardware in hand, while cycle-accurate simulation costs hours per configuration, leaving no tool for rapid, full-stack architectural reasoning. We present MLSYSIM (Machine Learning Systems Infrastructure Modeling), a first-principles analytical framework that formalizes the "physics of systems" into a dimensionally-strict Python engine. MLSysim is built on a demand-supply abstraction that decouples computational demand from silicon supply and environmental context, and it enforces unit integrity at runtime so the silent conversion errors that plague ad-hoc modeling cannot occur. Every input is drawn from a typed, provenance-tracked registry, so no number enters an analysis without a documented source. On this engine we codify a taxonomy of 22 "Systems Walls" resolved by 28 composable models and solvers, enabling sub-second design-space exploration that identifies binding constraints and synthesizes ideal hardware specifications across the entire ML systems lifecycle.

cs.DC↗
arXiv2026

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?

Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather than how to fix code. We introduce SWE-fficiency, a benchmark for evaluating repository-level performance optimization on real workloads. Our suite contains 498 tasks across nine widely used data-science, machine-learning, and HPC repositories (e.g., numpy, pandas, scipy): given a complete codebase and a slow workload, an agent must investigate code semantics, localize bottlenecks and relevant tests, and produce a patch that matches or exceeds expert speedup while passing the same unit tests. To enable this how-to-fix evaluation, our automated pipeline scrapes GitHub pull requests for performance-improving edits, combining keyword filtering, static analysis, coverage tooling, and execution validation to both confirm expert speedup baselines and identify relevant repository unit tests. Empirical evaluation of state-of-the-art agents reveals significant underperformance. On average, agents achieve less than 0.23x the expert speedup: agents struggle in localizing optimization opportunities, reasoning about execution across functions, and maintaining correctness in proposed edits. We release the benchmark and accompanying data pipeline to facilitate research on automated performance engineering and long-horizon software reasoning.

cs.SE↗
arXiv2026

AgentDSE: Reasoning-Augmented Architectural Design Space Exploration

Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlenecks, data reuse, and workload structures. To bridge this gap, we introduce AgentDSE, a simulator-in-the-loop methodology driven by a general-purpose large language model (LLM) coding agent. AgentDSE automates this architectural-reasoning loop without requiring model fine-tuning, precomputed design databases, or domain-specific optimizer code. Across deep neural network (DNN) accelerator mapping, hardware/software co-design, and CPU cache-hierarchy optimization, AgentDSE achieves competitive or better design quality with up to two orders of magnitude fewer evaluations. AgentDSE also produces inspectable traces that surface architectural hypotheses, performance cliffs, implicit priors, and simulator artifacts, making every search decision traceable rather than buried in optimizer state.

cs.AR↗
arXiv2026

Breaking TinyML: Why Quantized Neural Networks Need Domain-Specific Security Analysis

Most TinyML hardware accelerators focus on supporting Quantized Neural Networks (QNNs) to meet stringent constraints on power consumption and size. Despite this, the security aspects of quantization within TinyML hardware remain largely unexplored. Although previous studies indicate that QNNs demonstrate similar or enhanced robustness when compared to full-precision Deep Neural Networks (DNNs) against typical evasion attacks, no attack strategies tailored specifically for TinyML hardware have been proposed yet. This paper addresses this shortfall by demonstrating how a two-step attack pipeline can surpass the current state-of-the-art in the QNN context and shows the need for more hardware-aware security research.

cs.CR↗
arXiv2026

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple economic signals induce decentralized credit assignment, driving planning without global orchestration or explicit communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. We show that, initialized with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. We further provide theoretical insights into how economic dynamics shape agent behaviors, linking local incentives to long-term global performance. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

cs.CL↗
arXiv2026

MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces

The fast pace of artificial intelligence~(AI) innovation demands an agile methodology for observation, reproduction and optimization of distributed machine learning~(ML) workload behavior in production AI systems and enables efficient software-hardware~(SW-HW) co-design for future systems. We present Chakra, an open and portable ecosystem for performance benchmarking and co-design. The core component of Chakra is an open and interoperable graph-based representation of distributed AI/ML workloads, called Chakra execution trace~(ET). These ETs represent key operations, such as compute, memory, and communication, data and control dependencies, timing, and resource constraints. Additionally, Chakra includes a complementary set of tools and capabilities to enable the collection, analysis, generation, and adoption of Chakra ETs by a broad range of simulators, emulators, and replay tools. We present analysis of Chakra ETs collected on production AI clusters and demonstrate value via real-world case studies. Chakra has been adopted by MLCommons and has active contributions and engagement across the industry, including but not limited to NVIDIA, AMD, Meta, Keysight, HPE, and Scala, to name a few.

cs.DC↗
arXiv2026

JAXBench: Benchmarking Autonomous TPU Kernel Optimization

Rigorous benchmarks have driven progress in autonomous GPU kernel performance optimization by establishing a shared target to hillclimb on, but no equivalent exists for TPUs. We present JAXBench, a TPU-native benchmark suite for AI-generated kernel optimization on Google Cloud TPUs. JAXBench comprises 50 JAX workloads that are both relevant and provide headroom for optimization. We extract 17 production ML operators from architectures in the public MaxText library such as Llama-3.1, DeepSeek-V3, Mixtral, Mamba-2, and AlphaFold2, and translate 33 operators from KernelBench that are validated for correctness and set with new problem sizes that achieve high TPU v6e MXU utilization. Eight of the 17 production operators ship with hand-optimized Pallas kernels from the public Tokamax library and block-size tuned to establish an expert upper-bound baseline. We evaluate four feedback-driven methods on generating candidate Pallas kernels for JAXBench. Across the full suite with Gemini 3 Flash, we find that target-specific context matters more than model scale on a sparsely-documented DSL like Pallas. Conditioning on curated TPU documentation raises per-sample correctness from 5.8% to 37.3% and solves 48 of 50 benchmarks at a 1.28x geomean speedup. Search structure yields significant gains once correctness is achieved, with Autocomp's beam-search pipeline reaching a 1.36x geomean speedup over XLA. On the 8 hand-tuned kernels, Autocomp reaches 1.60x geomean over XLA, recovering most of the 2.08x Tokamax upper bound but trailing on the specialized paged and ragged attention operators. High-quality TPU kernel optimization remains a challenging task, and we release the JAXBench benchmark, evaluation harness, and baseline results to support open source contributions.

cs.AI↗
arXiv2026

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South

Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content.

cs.CY↗
arXiv2026

Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications

Tiny machine learning (TinyML) co-locates models with sensors on microcontrollers, where small models (which are disproportionately sensitive to label noise) and bespoke binary tasks (which lack standard benchmarks) make general-purpose dataset practices a poor fit. Visual Wake Words (VWW), the prior standard TinyML person detection benchmark, contains roughly 123K images and has an estimated label error rate of 7.8%, which limits its usefulness for production-grade systems. Manual labeling, however, is prohibitively expensive for the scale and diversity of TinyML use cases. We address this gap with the Wake Vision pipeline, an automated method for generating and curating large-scale binary classification datasets for TinyML. We use data-centric TinyML for the dataset construction, curation, and lifecycle methods that produce the large, well-curated datasets these systems require. The pipeline combines label fusion across image-level and bounding-box sources, confidence-, area-, and depiction-aware filtering, label correction on the evaluation splits, and automatic generation of fine-grained benchmark subsets. Applying it to person detection, we release Wake Vision, a dataset of almost 6M images (close to 100x more person images than VWW) with a manually relabeled validation and test set at a 2.2% label error rate. Models trained on Wake Vision improve test accuracy by up to 6.6% over VWW across MobileNetV2, MCUNet, MicroNets, and ColabNAS architectures, and match or exceed VWW-trained models on 13 of 16 fine-grained subsets covering perceived gender, perceived age, distance, lighting, and depictions. The advantage holds under distribution shift on three out-of-distribution datasets covering driving and overhead-surveillance imagery. All artifacts are released under CC-BY 4.0 through TensorFlow Datasets and Hugging Face.

cs.CV↗
arXiv2026

Lifetime-Aware Design for Item-Level Intelligence at the Extreme Edge

We present FlexiFlow, a lifetime-aware design framework for item-level intelligence (ILI) where computation is integrated directly into disposable products like food packaging and medical patches. Our framework leverages natively flexible electronics which offer significantly lower costs than silicon but are limited to kHz speeds and several thousands of gates. Our insight is that unlike traditional computing with more uniform deployment patterns, ILI applications exhibit 1000X variation in operational lifetime, fundamentally changing optimal architectural design decisions when considering trillion-item deployment scales. To enable holistic design and optimization, we model the trade-offs between embodied carbon footprint and operational carbon footprint based on application-specific lifetimes. The framework includes: (1) FlexiBench, a workload suite targeting sustainability applications from spoilage detection to health monitoring; (2) FlexiBits, area-optimized RISC-V cores with 1/4/8-bit datapaths achieving 2.65X to 3.50X better energy efficiency per workload execution; and (3) a carbon-aware model that selects optimal architectures based on deployment characteristics. We show that lifetime-aware microarchitectural design can reduce carbon footprint by 1.62X, while algorithmic decisions can reduce carbon footprint by 14.5X. We validate our approach through the first tape-out using a PDK for flexible electronics with fully open-source tools, achieving 30.9kHz operation. FlexiFlow enables exploration of computing at the Extreme Edge where conventional design methodologies must be reevaluated to account for new constraints and considerations.

cs.AR↗
arXiv2026

See it to Place it: Evolving Macro Placements with Vision-Language Models

We propose using Vision-Language Models (VLMs) for macro placement in chip floorplanning, a complex optimization task that has recently shown promising advancements through machine learning methods. Because human designers rely heavily on spatial reasoning to arrange components on the chip canvas, we hypothesize that VLMs with strong visual reasoning abilities can effectively complement existing learning-based approaches. We introduce VeoPlace (Visual Evolutionary Optimization Placement), a novel framework that uses a VLM, without any fine-tuning, to guide the actions of a base placer by constraining them to subregions of the chip canvas. The VLM proposals are iteratively optimized through an evolutionary search strategy with respect to resulting placement quality. On open-source benchmarks, VeoPlace outperforms the best prior learning-based approach on 9 of 10 benchmarks with peak wirelength reductions exceeding 32%. We further demonstrate that VeoPlace generalizes to analytical placers, improving DREAMPlace performance on all 8 evaluated benchmarks with gains up to 4.3%. Our approach opens new possibilities for electronic design automation tools that leverage foundation models to solve complex physical design problems.

cs.LG↗
arXiv2026

Slm-mux: Orchestrating small language models for reasoning

With the rapid development of language models, the number of small language models (SLMs) has grown significantly. Although they do not achieve state-of-the-art accuracy, they are more efficient and often excel at specific tasks. This raises a natural question: can multiple SLMs be orchestrated into a system where each contributes effectively, achieving higher accuracy than any individual model? Existing orchestration methods have primarily targeted frontier models (e.g., GPT-4) and perform suboptimally when applied to SLMs. To address this gap, we propose a three-stage approach for orchestrating SLMs. First, we introduce SLM-MUX, a multi-model architecture that effectively coordinates multiple SLMs. Building on this, we develop two optimization strategies: (i) a model selection search that identifies the most complementary SLMs from a given pool, and (ii) test-time scaling tailored to SLM-MUX. Our approach delivers strong results: Compared to existing orchestration methods, our approach achieves up to 13.4% improvement on MATH, 8.8% on GPQA, and 7.0% on GSM8K. With just two SLMs, SLM-MUX outperforms Qwen 2.5 72B on GPQA and GSM8K, and matches its performance on MATH. We further provide theoretical analyses to substantiate the advantages of our method. Additional experiments show that the core principle of SLM-MUX extends to open-ended generation tasks (e.g., HumanEval) and benefits other model classes, including frontier LLMs and domain-specific fine-tuned SLMs. In summary, we demonstrate that SLMs can be effectively orchestrated into more accurate and efficient systems through the proposed approach. The project page is available at https://slm-mux.github.io/.

cs.CL↗
arXiv2026

GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon

Generative AI is reshaping how computing systems are designed, optimized, and built, yet research remains fragmented across software, architecture, and chip design communities. This paper takes a cross-stack perspective, examining how generative models are being applied from code generation and distributed runtimes through hardware design space exploration to RTL synthesis, physical layout, and verification. Rather than reviewing each layer in isolation, we analyze how the same structural difficulties and effective responses recur across the stack. Our central finding is one of convergence. Despite the diversity of domains and tools, the field keeps encountering five recurring challenges (the feedback loop crisis, the tacit knowledge problem, trust and validation, co-design across boundaries, and the shift from determinism to dynamism) and keeps arriving at five design principles that independently emerge as effective responses (embracing hybrid approaches, designing for continuous feedback, separating concerns by role, matching methods to problem structure, and building on decades of systems knowledge). We organize these into a challenge--principle map that serves as a diagnostic and design aid, showing which principles have proven effective for which challenges across layers. Through concrete cross-stack examples, we show how systems navigate this map as they mature, and argue that the field needs shared engineering methodology, including common vocabularies, cross-layer benchmarks, and systematic design practices, so that progress compounds across communities rather than being rediscovered in each one. Our analysis covers more than 275 papers spanning eleven application areas across three layers of the computing stack, and distills open research questions that become visible only from a cross-layer vantage point.

cs.SE↗