Search arXiv⌕ Search

arXiv subjects

Mehdi Kamal

Publications and source records attributed to Mehdi Kamal.

At least 19 recordsLinked to original sources
arXiv2026

SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving

Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by running even fewer experts per token, and they are validated on accuracy benchmarks. We show that these methods can weaken the model's refusal of harmful requests, and we introduce SafeStart, which largely restores refusal while keeping most of the speedup. In vLLM on one RTX A6000, keeping about two thirds of the selected experts speeds up offline decoding by 15 to 28% at batch size 8. We find that, at this setting, under a jailbreak that tells the model not to refuse, the share of harmful requests that the model answers rises by 18.4 percentage points on Qwen1.5-MoE, 9.5 on OLMoE, and 6.6 on DeepSeek-V2-Lite, the three of nine models where it rises significantly, while MMLU accuracy drops by less than two points. We discover that most of this increase arises while the model processes the prompt and generates its first few tokens. SafeStart therefore runs all experts for the prompt and the first eight generated tokens, and the reduced set of experts afterwards, through a fused kernel in vLLM. With experts removed, SafeStart keeps at least 85% of the offline decode speedup at batch sizes 8 and 32 and brings the change under this jailbreak to between -2.1 and +1.3 points for three expert-reduction methods on these three models. On 889 held-out requests, in an analysis fixed before generation, truncation raises harmful compliance by 5.8 to 21.4 points, and SafeStart leaves a rise of 0.6 to 2.6 points, non-inferior to the original model on two of the three models. Our results show that faster MoE serving need not cost safety: a serving system can keep most of the gain from running fewer experts by running all of them at the start of each response, and it should test refusal, not only accuracy, before it enables such a method.

cs.AI↗
arXiv2026

C-GRPO: Conformal Group Relative Policy Optimization

Reasoning-oriented language model training increasingly relies on multiple on-policy rollouts, but standard Group Relative Policy Optimization (GRPO) uses a fixed group size, wasting compute on easy prompts and under-exploring hard ones. Existing adaptive-budget methods alleviate this inefficiency, yet their stopping rules are heuristic and do not provide a finite-sample calibration guarantee. We propose CGRPO, which replaces the fixed rollout budget of standard GPRO with calibrated conformal thresholds over task-specific nonconformity scores, combining Adaptive Prediction Set (APS)-style calibration for closed-form reasoning, a first-success score for execution-based code, automatic miscoverage selection, and periodic re-calibration. We prove finite-sample coverage for the resulting stopping rule and show that, under monotone policy improvement, recalibration induces a non-increasing expected training budget. Across six benchmarks spanning mathematics, graduate-level science, and code generation, CGRPO reduces mean training rollouts by 49-70% relative to fixed-budget GRPO while retaining strong fixed-budget accuracy, achieves the strongest pass@1 among evaluated static and dynamic baselines on different datasets, and transfers across model families with up to 82% rollout savings.

cs.LG↗
arXiv2026

Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding

Inference-time sequential Monte Carlo (SMC) decoding can improve the reasoning accuracy of masked diffusion language models (diffusion LLMs) without post-training by resampling a population of partial generations according to a reward. Its effectiveness therefore depends on the resampling step, which must concentrate computation on promising candidates while retaining enough diversity to explore alternative reasoning paths. The reward can be internal, the decoder's own confidence on the committed prefix, or external, a process reward model scoring that prefix. Under either reward, multinomial resampling can disrupt this balance by duplicating high-weight particles and discarding lineages that may still reach a correct solution. The effective sample size (ESS) does not register this loss: multinomial resampling resets it to its maximum even as distinct lineages disappear. To retain such lineages, we introduce lineage-preserving SMC (LP-SMC), which combines Chopthin resampling with an input weight floor. Instead of equalizing weights, Chopthin bounds the ratio between the largest and smallest weights it returns and carries the unequal weights forward. The floor limits how far below the maximum a weight may fall before resampling so that lineages with low early weight keep a chance to recover. Across mathematical-reasoning and code-generation benchmarks on two base models, LP-SMC raises oracle coverage, the fraction of problems with at least one correct particle, in every setting, by 1.8 to 25.6 points, and raises end-to-end accuracy under a common reward-model selector in eleven of twelve settings, by up to 7.9 points on LLaDA-1.5 and 18.3 on Dream-7B. The coverage gain persists under the external reward model, which suggests that diversity-preserving resampling and the guidance signal contribute separately to inference-time search.

cs.LG↗
arXiv2026

Claim Laundering: When Agent Decision Models Trust Records Over Reality

Agent decision models select actions in a single forward pass from inputs that combine environmental observations with the agent's own record of previous actions. When an action fails silently, these sources can conflict: the record reports success, but the environment shows that the step did not take effect. We ask which source determines the next decision. Across Android screen traces, ALFWorld, and WebShop, we construct paired states that independently vary the observation, the logged action, and an explicit success claim. In all 12 configurations of four decision models and three domains, records have a larger average effect on commitment decisions than observations; after claimed-but-failed steps, the models still stop, advance, or purchase in 53-100% of cases. Yet the relevant evidence is often represented internally: linear probes on intermediate hidden states distinguish successful from failed steps on held-out apps, tasks, and goals (AUROC 0.77-1.00), and activation patching reveals increasing influence from records in later layers. We use this signal in EVIGATE, an intermediate-layer veto that requires no additional forward pass and adds 0.04-2.0% serving latency. Under injected silent failures, EVIGATE improves task success by 18.7 points in live ALFWorld agents, 5.0 in WebShop, and 5.1 in a phone simulator, and in WebShop and the simulator it also outperforms random vetoes at the same rate. Its effectiveness depends on representative calibration states: gates calibrated on offline counterfactual states do not transfer reliably to live agent trajectories.

cs.AI↗
arXiv2026

Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding

Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existing SMC approaches rely on equal-weight resampling, which can aggressively prune low-weight trajectories, discarding potentially correct reasoning paths and degrading the genealogical diversity of the search space. To address this, we introduce Chopthin-Consensus Power Sampling (CCPS). Our method applies the Chopthin resampler to LLM decoding: rather than equalizing weights and forcing unnecessary particle duplication, it enforces an upper bound on the ratio between the largest and smallest weights and carries the unequal weights forward. This targeted intervention preserves a richer set of distinct reasoning paths, keeps the weighted SMC approximation unchanged in conditional expectation, and guarantees a lower bound on the post-resampling effective sample size (ESS). To fully exploit this enriched population, we employ a semantic-majority selection mechanism that merges token-identical final trajectories, clusters semantically equivalent answers, and returns the answer supported by the largest number of distinct trajectories. Evaluating across three open-weight models and five reasoning benchmarks, we show that Chopthin increases oracle coverage in 13 of 15 settings. Combined with semantic-majority selection, CCPS matches or exceeds the final-answer accuracy of the Power-SMC baseline in 14 of 15 settings, delivering absolute gains of up to 10.6 percentage points. These findings demonstrate that diversity-preserving resampling and diversity-aware selection are complementary mechanisms for training-free LLM reasoning. Code is available at github.com/MinooAhmadii/chopthin-consensus-power-sampling.

cs.CL↗
arXiv2026

The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow

Language-model agents sometimes act beyond their authorization and then misreport what they did. On CAPE-Bench, matched agent tasks in which one fact decides whether an action is authorized, frontier open-weight agents do both, and one behavior marks the lie: retroactive permission laundering, acting and then asking permission as if the action were pending, precedes a false report in 70% of 1081 fresh informed violations, against 8% otherwise (preregistered odds ratio 7.0); frontier agents on tau^2-bench instead fabricate the authorization before violating. A linear readout of the agent's residual stream forecasts the violation before the action (AUROC 0.94) and the false report before the report, and beats chain-of-thought monitors when the agent is pressured to hide its reasoning. Gating every proposed action on this forecast cuts violations over whole episodes in four model families, and sending repeated flags to an approver keeps authorized work (Gemma-4: violations 0.70 -> 0.09, completion 1.00; a model approver that escalates unclear cases keeps this gain with a person seeing 25% of asks), at about 10-8 of the agent's compute and 109 times less than a chain-of-thought monitor. On AgentDojo, an external prompt-injection benchmark, the same readout calibrated on 29 tasks, with the steering unchanged, cuts attack success on unseen tasks in two families (Gemma-4 11.7% -> 5.7%, gpt-oss 28.5% -> 17.5%) while keeping benign utility (Gemma-4 0.637 vs 0.637; gpt-oss 0.667 vs 0.681). Preventing the violation is also the most reliable way to prevent the lie (misreported violations 0.10 -> 0.01 pooled over three families, preregistered), whereas lie-specific fixes after a violation are weak. All tests are preregistered and hash-locked; code, data and the full record, including tests that did not pass, are at https://github.com/AryaFayyazi/Honesty.

cs.AI↗
arXiv2026

Stateless Stochastic Computing for Generative AI on Superconducting Logic: A Model-Hardware Co-Design

Thermodynamic computing lets stochastic physical dynamics carry out a computation and reads out the result as a time average. Recently, thermodynamic computing has been demonstrated on several hardware platforms, including digital CMOS circuits based on stochastic computing. Superconducting single-flux-quantum (SFQ) logic offers very high clock rates and very low switching energy, but it heavily penalizes state, memory, fan-out, and feedback, i.e., exactly the per-neuron accumulators on which such designs rely. We therefore realize thermodynamic computing in SFQ logic through a co-design of a generative model and its circuit in which the datapath holds no state at all. The model is a class-conditional flow-matching image generator, which transforms Gaussian noise into an image of the requested class along a short, deterministic path of four Euler steps; in hardware, these steps are unrolled into a feed-forward pipeline of stochastic bitstream operators, whose output is read out as a time average, as in thermodynamic computing, without any relaxation phase. Each layer of the model is a butterfly-factorized linear map built exclusively from multiplexers that operate on split-unipolar bitstreams. The ReLU activation, which in stochastic computing requires a per-neuron up/down counter (accounting for 60-70% of the JJs in a counter-based design), is replaced by a stateless AND-NOT gate whose one-clock input skew is provided at no cost by SFQ gate-level pipelining. The models are trained directly on the stream representation of the hardware, with a regularizer that bounds the stream gains. Synthesis with an SFQ design flow shows that stochastic streams tolerate relaxed path balancing, which reduces the Josephson-junction (JJ) count of a hard-wired stage by 40-47%.

cs.AR↗
arXiv2026

Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution

A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probability toward answers the model finds most likely (sharpening). Sampling from it improves reasoning without changing parameters, but needs many scored candidates per query. We show that a model can instead be trained to produce such answers in one generation. On-policy power distillation (OPPD) runs a sequential Monte Carlo sampler in which the model being trained generates candidates and a frozen teacher's power distribution weights them; the same probabilities weight each answer in a maximum-likelihood update. Training raises single-generation accuracy by up to 23.0 points on MATH500 and 27.3 on GSM8K over the untrained model at the same temperature, and one generation scores 2.4 and 3.5 points above published power sampling with 64 candidates, recovering 94 percent of the gain that 16 candidates give the untrained model. For context, against GRPO trained with verified rewards from the same checkpoint and budget, OPPD scores 3.8, 4.0 and 5.4 points higher on MATH500, GSM8K and AIME using no reference answers; the two are complementary, and OPPD applied after GRPO adds up to 9.3 points. Trained only on mathematics, OPPD raises HumanEval accuracy by up to 5.3 points. One loss coefficient moves the sharpening exponent the model absorbs between 1.19 and 2.02, against 1.14 for ordinary on-policy distillation, and it rises mostly on the model's own answers. Gains hold across model families and sizes, including a model already trained with verified rewards, where lowering the temperature gives nothing and OPPD adds 4.4 points on MATH500. Code: https://github.com/ArminAzizi98/OPPD.

cs.LG↗
arXiv2026

Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders

Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OBS) and hidden representation shift (IBS), measured through controlled counterfactual identity probes across gender, age, and race. Their relationship is summarized via Representation-Output Alignment (ROA), with quadrant diagnostics for identifying user-level hidden-output mismatch. Applied to six open-weight LLM families across three domains, FairGap reveals pervasive hidden-output decoupling: ROA rarely exceeds 0.22, and a non-negligible user population shows stable outputs despite substantial internal shifts, a mode that output-only audits cannot detect by design. Further, activation steering that reduces IBS by up to 8x simultaneously worsens OBS, demonstrating a fundamental tension between internal and output-level fairness that existing frameworks are unequipped to diagnose.

cs.AI↗
arXiv2026

Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors

The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design. In this work, we introduce Hybrid Modeling for Energy and Latency of LLMs (HYMELL), a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML). HYMELL models LLM execution through a three-level hierarchy: analytical estimation of primitive operations, ML prediction of higher-level components, and an end-to-end model that captures system-level overheads across both prefill and decode phases. The framework supports diverse architectures, including dense and mixture-of-experts (MoE) feed-forward networks (FFNs), as well as multi-head attention (MHA) and grouped-query attention (GQA) mechanisms. Evaluated on an NVIDIA H100 graphics processing unit (GPU), HYMELL achieves high predictive accuracy; notably, for LLaMA 3 8B, it attains less than 5% error for both prefill and decode phases. By predicting execution costs directly from architectural parameters, it enables fast, hardware-free design space exploration and energy-efficient optimization.

cs.LG↗
arXiv2026

COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models

Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language model. COFT operates in three stages. First, it creates a masked counterfactual prompt by replacing sensitive spans with neutral tokens. Second, it compares the factual and masked logit distributions through lightweight logit fusion to attenuate attribute-driven biases. Third, it uses dual-branch split-conformal calibration to certify per-step candidate token sets at a user-chosen risk level. We evaluate COFT across six models and multiple bias benchmarks. Our method reduces standard bias metrics by 30-55% (median 38%) while preserving task utility and language quality. Reasoning accuracies remain unchanged within run-to-run noise margins. The computational overhead is modest, equivalent to one additional cached forward pass (<=11%). COFT offers a clear, auditable path to safer CoT generation with significant bias reduction, negligible utility loss, and no requirement for retraining, auxiliary classifiers, or weight access.

cs.CL↗
arXiv2026

TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog

Early, tool-free prediction of post-synthesis timing remains a key obstacle to rapid RTL iteration. We introduce TimingLLM, a two-stage retrieval-augmented LLM pipeline that estimates worst negative slack (WNS) and total negative slack (TNS) directly from Verilog. Stage 1 is a fine-tuned LLM that acts as a compact post-synthesis timing oracle, producing path-level arrivals/required times that are summarized into lightweight structural-timing cues (e.g., bag-of-gates counts, critical-path depth, gate-type patterns). Stage 2 is an LLM-based regressor that predicts WNS/TNS and applies a learned diagonal steering vector at the last transformer block, computed from the k nearest timing-labeled modules in a disjoint retrieval bank. On VerilogEval, TimingLLM attains R_WNS = 0.91 (MAPE 12%) and R_TNS=0.97 (MAPE 16%) while running 1.3-1.6 times faster than prior methods. Training uses a new 60k-module Verilog corpus with synthesis reports, which we will release. After training once, TimingLLM can be adapted to new technology libraries and PVT corners by refitting only a small regression head on 1000 labeled modules per setting, consistently outperforming state-of-the-art baselines.

cs.AR↗
arXiv2026

HDLFORGE: A Two-Stage Multi-Agent Framework for Efficient Verilog Code Generation with Adaptive Model Escalation

We present HDLFORGE, a two-stage multi-agent framework for automated Verilog generation that optimizes the trade-off between generation speed and accuracy. The system uses a compact coder with a medium-sized LLM by default (Stage A) and escalates to a stronger coder with an ultra-large LLM (Stage B) only when needed, guided by a calibrated score from inexpensive diagnostics including compilation, lint, and smoke tests. A key innovation is a counterexample-guided formal agent that converts bounded-model-checking traces into reusable micro-tests, significantly reducing bug detection time and repair iterations. The portable escalation controller can wrap existing Verilog LLM pipelines without modifying their internals. Evaluated on VerilogEval Human, VerilogEval V2, and RTLLM benchmarks, HDLFORGE demonstrates improved accuracy-latency trade-offs compared to single-stage systems through comprehensive analysis of wall-clock time distributions, escalation thresholds, and agent ablations. On VerilogEval Human and VerilogEval V2, HDLFORGE-Qwen achieves 91.2% and 91.8% Pass@1 with roughly 50% lower median latency, dramatically improving accuracy over other medium-sized models, and 97.2% Pass@5 on RTLLM.

cs.AR↗
arXiv2025

SCE-NTT: A Hardware Accelerator for Number Theoretic Transform Using Superconductor Electronics

This research explores the use of superconductor electronics (SCE) for accelerating fully homomorphic encryption (FHE), focusing on the Number-Theoretic Transform (NTT), a key computational bottleneck in FHE schemes. We present SCE-NTT, a dedicated hardware accelerator based on superconductive single flux quantum (SFQ) logic and memory, targeting high performance and energy efficiency beyond the limits of conventional CMOS. To address SFQ constraints such as limited dense RAM and restricted fanin/fanout, we propose a deeply pipelined NTT-128 architecture using shift register memory (SRM). Designed for N=128 32-bit coefficients, NTT-128 comprises log2(N)=7 processing elements (PEs), each featuring a butterfly unit (BU), dual coefficient memories operating in ping-pong mode via FIFO-based SRM queues, and twiddle factor buffers. The BU integrates a Shoup modular multiplier optimized for a small area, leveraging precomputed twiddle factors. A new RSFQ cell library with over 50 parameterized cells, including compound logic units, was developed for implementation. Functional and timing correctness were validated using JoSIM analog simulations and Verilog models. A multiphase clocking scheme was employed to enhance robustness and reduce path-balancing overhead, improving circuit reliability. Fabricated results show the NTT-128 unit achieves 531 million NTT/sec at 34 GHz, over 100x faster than state-of-the-art CMOS equivalents. We also project that the architecture can scale to larger sizes, such as a 2^14-point NTT in approximately 482 ns. Key-switch throughput is estimated at 1.63 million operations/sec, significantly exceeding existing hardware. These results demonstrate the strong potential of SCE-based accelerators for scalable, energy-efficient secure computation in the post-quantum era, with further gains anticipated through advances in fabrication.

cs.AR↗
arXiv2025

MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering

This paper introduces MARCO (Multi-Agent Reinforcement learning with Conformal Optimization), a novel hardware-aware framework for efficient neural architecture search (NAS) targeting resource-constrained edge devices. By significantly reducing search time and maintaining accuracy under strict hardware constraints, MARCO bridges the gap between automated DNN design and CAD for edge AI deployment. MARCO's core technical contribution lies in its unique combination of multi-agent reinforcement learning (MARL) with Conformal Prediction (CP) to accelerate the hardware/software co-design process for deploying deep neural networks. Unlike conventional once-for-all (OFA) supernet approaches that require extensive pretraining, MARCO decomposes the NAS task into a hardware configuration agent (HCA) and a Quantization Agent (QA). The HCA optimizes high-level design parameters, while the QA determines per-layer bit-widths under strict memory and latency budgets using a shared reward signal within a centralized-critic, decentralized-execution (CTDE) paradigm. A key innovation is the integration of a calibrated CP surrogate model that provides statistical guarantees (with a user-defined miscoverage rate) to prune unpromising candidate architectures before incurring the high costs of partial training or hardware simulation. This early filtering drastically reduces the search space while ensuring that high-quality designs are retained with a high probability. Extensive experiments on MNIST, CIFAR-10, and CIFAR-100 demonstrate that MARCO achieves a 3-4x reduction in total search time compared to an OFA baseline while maintaining near-baseline accuracy (within 0.3%). Furthermore, MARCO also reduces inference latency. Validation on a MAX78000 evaluation board confirms that simulator trends hold in practice, with simulator estimates deviating from measured values by less than 5%.

cs.LG↗
arXiv2025

RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts

This paper presents RocketPPA, a novel ultra-fast power, performance (delay), and area (PPA) estimator operating directly at the code-level abstraction using HDL code as input. The key technical innovation is its LLM-based regression model, which uniquely integrates a large language model (LLM) with a mixture-of-experts (MoE) architecture composed of multilayer perceptrons (MLPs). The LLM interprets the input HDL code and then utilizes its final hidden-layer representations to predict PPA metrics. Low-rank adaptation (LoRA) is used for parameter-efficient fine-tuning to enable efficient LLM training. Furthermore, the work includes the development of an LLM-based HDL code repair framework to generate a large and synthesizable training dataset. Experimental results on the VerilogEval benchmark demonstrate that RocketPPA achieves significant improvements in the accuracy of PPA estimation compared to previous state-of-the-art methods like Llama3-MetRex-8B. Specifically, at a 10% relative error threshold, RocketPPA enhances the pass rate for area prediction by 13.6%, delay by 9.4%, and power by 14.7%. At a 20% threshold, the improvements are 9.6% for area, 10.8% for delay, and 18.5% for power. Moreover, RocketPPA achieves a speedup of over 20x compared to MetRex and 30x over MasterRTL in processing the test set. The impact of RocketPPA is the potential to substantially accelerate the hardware design process by providing accurate PPA estimations early in the design cycle, thus avoiding the overhead of manual feature engineering and time-consuming synthesis flows.

cs.LG↗
arXiv2025

FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair

We introduce FAIR-SIGHT, an innovative post-hoc framework designed to ensure fairness in computer vision systems by combining conformal prediction with a dynamic output repair mechanism. Our approach calculates a fairness-aware non-conformity score that simultaneously assesses prediction errors and fairness violations. Using conformal prediction, we establish an adaptive threshold that provides rigorous finite-sample, distribution-free guarantees. When the non-conformity score for a new image exceeds the calibrated threshold, FAIR-SIGHT implements targeted corrective adjustments, such as logit shifts for classification and confidence recalibration for detection, to reduce both group and individual fairness disparities, all without the need for retraining or having access to internal model parameters. Comprehensive theoretical analysis validates our method's error control and convergence properties. At the same time, extensive empirical evaluations on benchmark datasets show that FAIR-SIGHT significantly reduces fairness disparities while preserving high predictive performance.

cs.CV↗
arXiv2025

Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance

This paper introduces a novel Dynamic Co-Optimization Compiler (DCOC), which employs an adaptive Multi-Agent Reinforcement Learning (MARL) framework to enhance the efficiency of mapping machine learning (ML) models, particularly Deep Neural Networks (DNNs), onto diverse hardware platforms. DCOC incorporates three specialized actor-critic agents within MARL, each dedicated to different optimization facets: one for hardware and two for software. This cooperative strategy results in an integrated hardware/software co-optimization approach, improving the precision and speed of DNN deployments. By focusing on high-confidence configurations, DCOC effectively reduces the search space, achieving remarkable performance over existing methods. Our results demonstrate that DCOC enhances throughput by up to 37.95% while reducing optimization time by up to 42.2% across various DNN models, outperforming current state-of-the-art frameworks.

cs.LG↗