arXiv subjects

Vahid Partovi Nia

Publications and source records attributed to Vahid Partovi Nia.

At least 19 recordsLinked to original sources

arXiv2026

Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization

Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model depth. Existing approaches such as Multi-Query Attention (MQA), Grouped-Query Attention (GQA), Multi-Head Latent Attention (MLA), and Tensor Product Attention (TPA) reduce this cost through different trade-offs, but often sacrifice expressivity, require additional positional-encoding machinery, or impose restrictive low-rank structure. We propose Kronecker Product Attention (KPA), which represents key and value activations as sums of Kronecker products of compact, token-dependent matrix factors. KPA strictly generalizes TPA: rank-one vector-outer-product factorization arises as a degenerate Kronecker split, while non-degenerate matrix factors can represent richer block-structured patterns. We further show that a structured rotary embedding operator matched to the Kronecker representation preserves the relative-position property of RoPE while rotating only the compact factors, removing the need for a decoupled RoPE branch as in MLA. Empirically, KPA matches or exceeds TPA, MHA, MQA, GQA, and MLA across four model scales and nine downstream benchmarks under identical training conditions, while achieving up to 10x KV cache compression. The Kronecker head split is a tuneable hyperparameter that allows practitioners to navigate the compression-accuracy trade-off at design time without architectural changes.

cs.LG↗

arXiv2026

Conformal Prediction under Partial Verification

Conformal prediction provides prediction sets with finite-sample guarantees, but the label verification required for calibration can be expensive. We develop a partial verification method that returns exactly the same prediction sets as complete verification. We characterize calibration certificates, the verified information sufficient to determine the conformal threshold, and design a procedure that coordinates verification across calibration examples. For finite thresholds at high coverage, its verification cost is less than twice the minimum certificate cost when candidates are checked in order. Across retrieval, mathematical solutions, and configuration evaluation, it reduces verification cost by 15-82% compared with verifying calibration examples one at a time, while producing identical prediction sets.

stat.ML↗

arXiv2026

From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls

In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, and the highest Seen accuracy in our main grid occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with a higher inference cost, chiefly the latency of processing the schema prompt. Our theoretical analysis formalizes why only SIP can predict functions withheld as training targets and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.

cs.LG↗

arXiv2026

G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm

Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a later action sends that data outside the system. We introduce CARB (Conformal Agent Risk Budget), which calibrates when to stop an agent using a ledger of harm incurred before stopping. Under exchangeable episodes, standard conformal risk control bounds this declared loss in expectation over calibration and a future episode. G-CARB selects scorer evidence along observable dependencies from private sources to outgoing actions. The ledger still covers the entire executed history, and computing the gate score requires no additional language-model inference. On AgentDojo replay with two 14B backbones, G-CARB roughly halves scorer-input records at intermediate risk budgets while improving autonomous task completion relative to full-prefix scoring; random context of the same size achieves similar gains. Controlled examples show how retaining the relevant dependency can further avoid stopping benign work.

stat.ML↗

arXiv2026

HyWA: Architecture-Preserving Personalized Voice Activity Detection for Full-Duplex Voice Assistants

Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices. Because conventional VADs respond to speech from any speaker, nearby conversations and residual assistant playback lead to unwanted triggers, degrade the user experience, and waste computational resources. Personalized voice activity detection (PVAD) addresses this limitation by detecting speech only from an enrolled target speaker. Existing PVAD methods typically incorporate speaker information into model inputs or hidden representations. These approaches require VAD architectural changes that increase engineering and requalification costs in deployment. We present HyWA, a hypernetwork-based weight-adaptation method that converts an established VAD into a PVAD, while preserving its acoustic interface and inference topology. HyWA generates speaker-conditioned weights once at enrollment and requires no per-user optimization. We apply HyWA to pretrained Alibaba's FSMN and NVIDIA's MarbleNet VAD models. Evaluations on synthetic and real-user test data show consistent improvements in target-speaker discrimination and false-positive suppression. In an integrated full-duplex barge-in pipeline, replacing generic VAD with HyWA-based PVAD reduces observed false-interruption detections from 88.9% to only 9.9%.

eess.AS↗

arXiv2026

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregation rule over a pool of candidate paths, making aggregation uncertainty the central challenge. This issue is critical where confidently incorrect answers are far more costly than abstentions. We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty. Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control. This approach leads to finite-sample guarantees on the confident-error rate--the probability that the system answers and is wrong. We further identify score separability as the key condition under which abstention provably improves selective accuracy, and derive closed-form expressions that predict accuracy gains from calibration data alone. The method is fully inference-time, and requires no retraining. Across four benchmarks, four open-source models, and three score classes, realized confident-error rates are consistent with the prescribed targets up to calibration-split and test-set variability. Our method achieves $90.1\%$ selective accuracy on GSM8K by abstaining on less than $5\%$ of problems, compared with $82\%$ accuracy under majority-voting baseline.

stat.ML↗

arXiv2026

Enterprise Resource Planning Using Multi-type Transformers in Ferro-Titanium Industry

Combinatorial optimization problems such as the Job-Shop Scheduling Problem (JSP) and Knapsack Problem (KP) are fundamental challenges in operations research, logistics, and eterprise resource planning (ERP). These problems often require sophisticated algorithms to achieve near-optimal solutions within practical time constraints. Recent advances in deep learning have introduced transformer-based architectures as promising alternatives to traditional heuristics and metaheuristics. We leverage the Multi-Type Transformer (MTT) architecture to address these benchmarks in a unified framework. We present an extensive experimental evaluation across standard benchmark datasets for JSP and KP, demonstrating that MTT achieves competitive performance on different size of these benchmark problems. We showcase the potential of multi-type attention on a real application in Ferro-Titanium industry. To the best of our knowledge, we are the first to apply multi-type transformers in real manufacturing.

cs.AI↗

arXiv2025

MoKA: Mixture of Kronecker Adapters

Parameter-efficient fine-tuning (PEFT) is essential for reducing the computational overhead of large language models (LLMs). Low-rank family adapters are commonly used to control the parameter size efficiently while maintaining the generative power of LLMs. However, their limited expressiveness due to the rank constraint often restricts their performance on complex tasks. We propose Mixture of Kronecker Adapters (MoKA), a new generation of Kronecker adapters that addresses this limitation by modeling weight updates as a mixture of Kronecker products. Our proposed adapter leverages a gating mechanism that measures the importance of each Kronecker factor, enabling more expressive adaptation. Moreover, MoKA enables a rank flexibility that provides a better trade-off between parameter efficiency and accuracy. To ensure hardware efficiency, we reformulate Kronecker computations using standard matrix operations, allowing seamless deployment on GPU-optimized hardware. We conduct extensive experiments on instruction-tuning and commonsense reasoning tasks using low-bit quantized versions of LLaMA2-7B and LLaMA3-8B models. MoKA not only outperforms PEFT baselines, but also reduces the number of trainable parameters up to 27x, achieving state-of-the-art trade-offs between performance and parameter efficiency.

cs.LG↗

arXiv2025

Tiny Noise-Robust Voice Activity Detector for Voice Assistants

Voice Activity Detection (VAD) in the presence of background noise remains a challenging problem in speech processing. Accurate VAD is essential in automatic speech recognition, voice-to-text, conversational agents, etc, where noise can severely degrade the performance. A modern application includes the voice assistant, specially mounted on Artificial Intelligence of Things (AIoT) devices such as cell phones, smart glasses, earbuds, etc, where the voice signal includes background noise. Therefore, VAD modules must remain light-weight due to their practical on-device limitation. The existing models often struggle with low signal-to-noise ratios across diverse acoustic environments. A simple VAD often detects human voice in a clean environment, but struggles to detect the human voice in noisy conditions. We propose a noise-robust VAD that comprises a light-weight VAD, with data pre-processing and post-processing added modules to handle the background noise. This approach significantly enhances the VAD accuracy in noisy environments and requires neither a larger model, nor fine-tuning. Experimental results demonstrate that our approach achieves a notable improvement compared to baselines, particularly in environments with high background noise interference. This modified VAD additionally improving clean speech detection.

eess.AS↗

arXiv2025

PoTPTQ: A Two-step Power-of-Two Post-training for LLMs

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, their deployment is challenging due to the substantial computational resources required. Power-of-two (PoT) quantization is a general tool to counteract this difficulty. Albeit previous works on PoT quantization can be efficiently dequantized on CPUs using fixed-point addition, it showed less effectiveness on GPUs. The reason is entanglement of the sign bit and sequential bit manipulations needed for dequantization. We propose a novel POT quantization framework for LLM weights that (i) outperforms state-of-the-art accuracy in extremely low-precision number formats, and (ii) enables faster inference through more efficient dequantization. To maintain the accuracy of the quantized model, we introduce a two-step post-training algorithm: (i) initialize the quantization scales with a robust starting point, and (ii) refine these scales using a minimal calibration set. The performance of our PoT post-training algorithm surpasses the current state-of-the-art in integer quantization, particularly at low precisions such as 2- and 3-bit formats. Our PoT quantization accelerates the dequantization step required for the floating point inference and leads to $3.67\times$ speed up on a NVIDIA V100, and $1.63\times$ on a NVIDIA RTX 4090, compared to uniform integer dequantization.

cs.CL↗

arXiv2025

OAC: Output-adaptive Calibration for Accurate Post-training Quantization

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization (PTQ) techniques have been developed to compress LLMs while avoiding expensive re-training. Most PTQ approaches formulate the quantization error based on a layer-wise Euclidean loss, ignoring the model output. Then, each layer is calibrated using its layer-wise Hessian to update the weights towards minimizing the quantization error. The Hessian is also used for detecting the most salient weights to quantization. Such PTQ approaches are prone to accuracy drop in low-precision quantization. We propose Output-adaptive Calibration (OAC) to incorporate the model output in the calibration process. We formulate the quantization error based on the distortion of the output cross-entropy loss. OAC approximates the output-adaptive Hessian for each layer under reasonable assumptions to reduce the computational complexity. The output-adaptive Hessians are used to update the weight matrices and detect the salient weights towards maintaining the model output. Our proposed method outperforms the state-of-the-art baselines such as SpQR and BiLLM, especially, at extreme low-precision (2-bit and binary) quantization.

cs.LG↗

arXiv2025

Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach

As Large Language Models (LLMs) become increasingly computationally complex, developing efficient deployment strategies, such as quantization, becomes crucial. State-of-the-art Post-training Quantization (PTQ) techniques often rely on calibration processes to maintain the accuracy of these models. However, while these calibration techniques can enhance performance in certain domains, they may not be as effective in others. This paper aims to draw attention to robust statistical approaches that can mitigate such issues. We propose a weight-adaptive PTQ method that can be considered a precursor to calibration-based PTQ methods, guiding the quantization process to preserve the distribution of weights by minimizing the Kullback-Leibler divergence between the quantized weights and the originally trained weights. This minimization ensures that the quantized model retains the Shannon information content of the original model to a great extent, guaranteeing robust and efficient deployment across many tasks. As such, our proposed approach can perform on par with most common calibration-based PTQ methods, establishing a new pre-calibration step for further adjusting the quantized weights with calibration. We show that our pre-calibration results achieve the same accuracy as some existing calibration-based PTQ methods on various LLMs.

cs.LG↗

arXiv2024

AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs

The ever-growing computational complexity of Large Language Models (LLMs) necessitates efficient deployment strategies. The current state-of-the-art approaches for Post-training Quantization (PTQ) often require calibration to achieve the desired accuracy. This paper presents AdpQ, a novel zero-shot adaptive PTQ method for LLMs that achieves the state-of-the-art performance in low-precision quantization (e.g. 3-bit) without requiring any calibration data. Inspired by Adaptive LASSO regression model, our proposed approach tackles the challenge of outlier activations by separating salient weights using an adaptive soft-thresholding method. Guided by Adaptive LASSO, this method ensures that the quantized weights distribution closely follows the originally trained weights and eliminates the need for calibration data entirely, setting our method apart from popular approaches such as SpQR and AWQ. Furthermore, our method offers an additional benefit in terms of privacy preservation by eliminating any calibration or training data. We also delve deeper into the information-theoretic underpinnings of the proposed method. We demonstrate that it leverages the Adaptive LASSO to minimize the Kullback-Leibler divergence between the quantized weights and the originally trained weights. This minimization ensures the quantized model retains the Shannon information content of the original model to a great extent, guaranteeing efficient deployment without sacrificing accuracy or information. Our results achieve the same accuracy as the existing methods on various LLM benchmarks while the quantization time is reduced by at least 10x, solidifying our contribution to efficient and privacy-preserving LLM deployment.

cs.CL↗

arXiv2024

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers

In neural network binarization, BinaryConnect (BC) and its variants are considered the standard. These methods apply the sign function in their forward pass and their respective gradients are backpropagated to update the weights. However, the derivative of the sign function is zero whenever defined, which consequently freezes training. Therefore, implementations of BC (e.g., BNN) usually replace the derivative of sign in the backward computation with identity or other approximate gradient alternatives. Although such practice works well empirically, it is largely a heuristic or ''training trick.'' We aim at shedding some light on these training tricks from the optimization perspective. Building from existing theory on ProxConnect (PC, a generalization of BC), we (1) equip PC with different forward-backward quantizers and obtain ProxConnect++ (PC++) that includes existing binarization techniques as special cases; (2) derive a principled way to synthesize forward-backward quantizers with automatic theoretical guarantees; (3) illustrate our theory by proposing an enhanced binarization algorithm BNN++; (4) conduct image classification experiments on CNNs and vision transformers, and empirically verify that BNN++ generally achieves competitive results on binarizing these models.

cs.LG↗

arXiv2024

Mitigating Outlier Activations in Low-Precision Fine-Tuning of Language Models

Low-precision fine-tuning of language models has gained prominence as a cost-effective and energy-efficient approach to deploying large-scale models in various applications. However, this approach is susceptible to the existence of outlier values in activation. The outlier values in the activation can negatively affect the performance of fine-tuning language models in the low-precision regime since they affect the scaling factor and thus make representing smaller values harder. This paper investigates techniques for mitigating outlier activation in low-precision integer fine-tuning of the language models. Our proposed novel approach enables us to represent the outlier activation values in 8-bit integers instead of floating-point (FP16) values. The benefit of using integers for outlier values is that it enables us to use operator tiling to avoid performing 16-bit integer matrix multiplication to address this problem effectively. We provide theoretical analysis and supporting experiments to demonstrate the effectiveness of our approach in improving the robustness and performance of low-precision fine-tuned language models.

cs.CL↗

arXiv2023

DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization

Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. To address this issue, researchers have proposed multiplication-free neural networks, such as Power-of-Two quantization, or also known as Shift networks, which aim to reduce memory usage and simplify computation. However, existing low-bit Shift networks are not as accurate as their full-precision counterparts, typically suffering from limited weight range encoding schemes and quantization loss. In this paper, we propose the DenseShift network, which significantly improves the accuracy of Shift networks, achieving competitive performance to full-precision networks for vision and speech applications. In addition, we introduce a method to deploy an efficient DenseShift network using non-quantized floating-point activations, while obtaining 1.6X speed-up over existing methods. To achieve this, we demonstrate that zero-weight values in low-bit Shift networks do not contribute to model capacity and negatively impact inference computation. To address this issue, we propose a zero-free shifting mechanism that simplifies inference and increases model capacity. We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance. Our extensive experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks and achieves competitive performance compared to full-precision networks. Furthermore, our proposed approach exhibits strong transfer learning performance without a drop in accuracy. Our code was released on GitHub.

cs.CV↗

arXiv2023

Mathematical Challenges in Deep Learning

Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012. The size of deep models is increasing ever since, which brings new challenges to this field with applications in cell phones, personal computers, autonomous cars, and wireless base stations. Here we list a set of problems, ranging from training, inference, generalization bound, and optimization with some formalism to communicate these challenges with mathematicians, statisticians, and theoretical computer scientists. This is a subjective view of the research questions in deep learning that benefits the tech industry in long run.

cs.LG↗

arXiv2023

Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation

The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously researchers were focused on lower bit-width integer data types for the forward propagation of language models to save memory and computation. As for the backward propagation, however, only 16-bit floating-point data type has been used for the fine-tuning of BERT. In this work, we use integer arithmetic for both forward and back propagation in the fine-tuning of BERT. We study the effects of varying the integer bit-width on the model's metric performance. Our integer fine-tuning uses integer arithmetic to perform forward propagation and gradient computation of linear, layer-norm, and embedding layers of BERT. We fine-tune BERT using our integer training method on SQuAD v1.1 and SQuAD v2., and GLUE benchmark. We demonstrate that metric performance of fine-tuning 16-bit integer BERT matches both 16-bit and 32-bit floating-point baselines. Furthermore, using the faster and more memory efficient 8-bit integer data type, integer fine-tuning of BERT loses an average of 3.1 points compared to the FP32 baseline.

cs.LG↗