Quantization
-
Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages
Abstract
Aggressive quantization disproportionately harms multilingual capability: in the sub-4B INT3 GPTQ regime, we measure 2-4x larger perplexity degradation on non-English languages than on English. We propose Language-Conditional Dequantization (LCD), a post-hoc method that attaches per-language rank-2 LoRA corrections to the linear layers of an already-quantized model, adding 0.12% parameters per language and training in under 20 minutes on a single GPU. Across Qwen2.5-3B and Llama-3.2-3B, LCD recovers 70-83% of the perplexity gap for non-Latin script languages and 17-28% of the GlobalMMLU accuracy gap, outperforming a language-agnostic correction of equal capacity by 3-9 points on typologically distant languages and a data-free low-rank baseline (LQER) by an order of magnitude. We further identify a perplexity-accuracy disconnect and trace it to where quantization concentrates damage: early-depth errors (Llama) propagate downstream and resist local correction, while late-depth errors (Qwen) do not. A layer-restricted variant of LCD validates this mechanism directly.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11786
PDF
-
Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines
2026-08-12 08:14:22Vaishnav RajuAbstract
Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11770
PDF
-
Luna-TTS Family Technical Report
2026-08-12 03:07:07Feng Yin, Shuai Shi, Junjie Zheng, Kechenying Zhou, Yiqiu Wang, Chenyang He, Qiuhua Jiang, Mengxiao Bi, Yanmin Qian, Mingxin Chen, Xun Gong, Tianteng Gu, Bing Han, Peng Jiang, Chenda Li, Haiyang Sun, Han Wang, Wei Wang, Yi Wang, Leying Zhang, Wangyou Zhang, Chushu ZhouAbstract
Modern text-to-speech (TTS) is dominated by autoregressive (AR) codec language models, whose left-to-right decoding brings latency that grows with utterance length, error accumulation along the committed prefix, and an artificial generation order imposed on the Residual Vector Quantization (RVQ) token grid. We propose Luna-TTS Family, diffusion-language-model-based TTS systems pretrained on 1 million hours of speech across Chinese, English, Japanese, and Korean. The family is built by progressive adaptation of a pretrained AR text LLM, from causal to bidirectional and finally to block-causal attention, and comprises two variants sharing a single tokenizer, data pipeline, and 0.6B backbone lineage. Luna-TTS is fully non-autoregressive: it generates the entire RVQ token grid in a fixed number of parallel refinement steps, with zero-shot voice cloning and speech editing arising natively as infilling. Luna-TTS Realtime, derived by continual training, is autoregressive over blocks of 32 codec frames (1.28s) while denoising each block in parallel; it supports KV-cached blockwise generation and incremental audio delivery, achieving an end-to-end RTF of 0.0240 and 41.6 ms local first-block latency under the warmed serving protocol. An annealed fine-tuning stage adds explicit control over emotion and non-verbal vocalizations (NVVs), and a reinforcement-learning stage applies GRPO with policy ratios computed over the realized denoising trajectory. On Seed-TTS-Eval, Luna-TTS achieves the best results on all four metrics among compared open-source and commercial systems (0.73 CER / 79.7 SIM on test-zh, 1.49 WER / 76.8 SIM on test-en); on the harder in-the-wild CV3-Eval, it posts the lowest Mandarin and English error rates in our comparison. Against leading commercial systems, it achieves the best results on most objective, model-based, and human-rated metrics for NVV and emotion control.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11593
PDF
-
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
2026-08-11 15:18:07He-Yen Hsieh, H. T. KungAbstract
ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting from a pretrained LLM, ReRound trains a conditional diffusion model to produce continuous reconstructions of low-bit weights for the LLM. These reconstructed weights act as a guidance signal to disambiguate the rounding direction of weights located close to interval midpoints. To integrate this reconstruction-guided rounding with conventional RTN, ReRound introduces a tolerance metric measuring how far the quantized weight (not the final quantized integer) is away from the midpoint: quantized weights within a tolerance region around midpoints are quantized using diffusion-based reconstructions, whereas weights closer to quantization boundaries are quantized with RTN. By sweeping the tolerance parameter, ReRound generates multiple candidate quantized integer weight matrices and selects the de-quantized weight matrix candidate whose leading singular values most closely match those of the original full-precision weights. This selected candidate determines the tolerance parameter ReRound uses. ReRound is particularly effective for smaller LLMs. Across a range of such models, it consistently outperforms standard RTN for 3-bit and 4-bit weight quantization. ReRound achieves superior accuracy compared to an extensive set of calibration-free methods, remains competitive with calibration-dependent approaches, and operates entirely offline, introducing no additional overhead during low-bit inference. The ReRound strategy represents a new approach for low-bit quantization. The method applies to AI models beyond LLMs. This paper focuses on its applications to small LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11045
PDF
-
Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation
2026-08-11 10:45:37Javad Zolfaghari-Bengar, Rakibul Rony, Elisa Gomez-de-Lope, Alejandro Villena-Rodriguez, Abhinav Mahadevan, Nicolas KourtellisAbstract
This demo presents real-time AI-based uplink channel-estimation inference using data collected from a hardware-in-the-loop 5G platform. The data-collection setup integrates commercial RF signal generation, programmable channel emulation, an O-RAN Radio Unit, DU emulation, and a lightweight phase-aware convolutional neural network (CNN) that estimates the channel response directly from received DMRS signals. Unlike simulation-only evaluations, the hardware-derived dataset exposes the estimator to practical RF and system-level impairments, including calibration mismatches, synchronization imperfections, quantization effects, phase noise, and implementation-specific nonlinearities. During the demo, attendees will observe real-time CNN inference and channel reconstruction using captured hardware-generated DMRS observations and compare the proposed CNN against Least Squares (LS) and frequency-domain LMMSE baselines. The objective is to showcase a practical AI-native physical-layer inference pipeline that combines hardware-derived 5G data with real-time neural channel estimation for future 5G-Advanced and 6G systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14709
PDF
-
Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits
2026-08-11 06:06:12Ricardo Parada, Chenzhang Zhao, William ChangAbstract
Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We consider three information structures: (A)~unobserved actions with common rewards, (B)~observed actions with independent rewards, and (C)~unobserved actions with independent rewards. In each case we design and analyze an algorithm that estimates the Lipschitz constant, chooses a discretization of the joint action space, and applies a cooperative bandit method to the induced discrete problem. Players never communicate once learning starts, so the central difficulty is that they must reach the \emph{same} discretization from their own data. We prove regret guarantees showing that common rewards and observable actions each supply this agreement for free, and that in their absence agreement can still be bought, through a dithered quantization of the estimate, at no cost in the leading order of the regret.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10526
PDF
-
TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers
2026-08-11 00:27:07Xiaoqin Feng, Yuqi Li, Weilun Feng, Yi-Cheng Lin, Kai Li, Xianglong Wang, Kuo Yang, Chuanguang Yang, Yingli Tian, Wei Li, Zhongwei Cheng, Lin ChenAbstract
Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size and multi-step sampling put them out of reach of the on-device, assistive, and real-time applications that need them most. Post-training quantization (PTQ) shrinks such models without retraining, but it has been built for language and vision, not speech. At 4 bits, a strong quantizer leaves intelligibility close to full precision but consistently erodes speaker timbre, so error rates stay low while the voice drifts from the target speaker. We ask why quantization hurts speech, where the damage lives, and whether it can be repaired without retraining. To find out, we run the first 4-bit weight-and-activation (W4A4) PTQ study of a TTS diffusion transformer at 1B and 3.5B. The timbre cost comes from both the weight and the activation quantization, but only the activation part has the timestep structure a precision schedule can exploit. We therefore introduce TTS-Q, which selects hard-to-quantize items from task-matched calibration candidates and applies a budget-balanced mixed-precision schedule that assigns higher precision to late-step feed-forward activations. TTS-Q recovers timbre best at both scales, at no cost to intelligibility. Separately, the deployed calibrated-W4A4 reference reduces peak memory on GPU, providing a practical reference for resource-constrained TTS deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12474
PDF
-
Decodable But Not Detachable: Training Data Granularity Determines Parametric Modularity in Large Language Models
2026-08-10 20:35:43Marcus Armstrong, Navid Ayoobi, Arjun MukherjeeAbstract
Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain while sparing others? We apply a uniform causal methodology across two domain granularities, three model families (1.5B to 7B parameters), and eight domains. At the academic subject level, zero neurons exceed 60\% domain selectivity across 939,008 combined FFN neurons and causal damage matrices are flat, despite domain identity being linearly decodable above 85\% accuracy. At the language and modality level, 0.65--1.14\% of neurons exceed 60\% selectivity, damage matrices are near-perfectly diagonal (ratios up to 595:1), and shell neuron sets are essentially disjoint (IoU $< 0.003$). Masking code-selective neurons reduces mathematical reasoning accuracy by 16--24 percentage points across all models; masking Spanish or Chinese neurons leaves it at or below random. Shell strength increases monotonically with scale and shells are spatially interleaved in a pattern that precludes group-level selective quantization. Parametric shells form where and only where training data was modular at the token level.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10214
PDF
-
Entropy-Constrained Adaptive Stochastic Quantization
2026-08-10 17:32:40Ran Ben Basat, Yaniv Ben-Itzhak, Michael Mitzenmacher, Shay VargaftikAbstract
Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness. It is designed to alleviate the communication and memory bottlenecks of modern data and machine learning workloads, including model, gradient, and KV-cache compression and nearest-neighbor search. Further, practical systems can then compress quantized data with a lossless entropy encoder. However, existing unbiased methods, including ASQ, choose their quantization values without considering this later encoding stage, leaving accuracy on the table. We formulate the Entropy Constrained Adaptive Stochastic Quantization (ECASQ) problem, which jointly selects adaptive quantization values to minimize MSE under an entropy budget and an unbiasedness constraint. We give an optimal dynamic program with $O(sd^2)$ time and $O(d^2)$ space for a length-d vector and at most s quantization values, and a GPU-friendly approximate dynamic program with $O(sd^2)$ time and $O(d)$ space. The approximation guarantees that the solution has an MSE no larger than the optimal solution that uses one fewer bit of entropy per entry. We also provide an iterative refinement procedure for the approximation solution that, in our experiments, yields near-optimal results while retaining a substantial speed advantage over our solver for the optimal solution.
Abstract (translated)
URL
https://arxiv.org/abs/2608.18147
PDF
-
From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization
2026-08-10 13:28:23Achille Jacquemond, Yuma Ichikawa, Akira SakaiAbstract
Compressing large language models to two bits or fewer is increasingly feasible through block-wise post-training quantization; cross-block variants reconstruct neighboring Transformer blocks within a moving window. In the fixed two-block setting studied here, the matched sequential baseline moves this window through the network once, so errors introduced early in the sweep are not revisited. We propose Interleaved Cross-Block Quantization (ICBQ), a scheduling modification that revisits the boundary pair between consecutive chunks. Each seam pair is refined twice: first at the end of one chunk and again at the start of the next. The method retains the local two-block objective and reuses the calibration inputs of existing block-wise PTQ pipelines. Under stated local contraction and smoothness assumptions, we derive a depth-wise upper-bound comparison in which seam revisits multiply the propagated term while the residual remains bounded independently of depth. In the reported experiments, ICBQ reduces ternary-quantization perplexity relative to the matched Sequential CBQ baseline, yields finite perplexity in configurations where the baseline has severe degradation, and can also be used with 3-bit and 2-bit GPTQ.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09595
PDF
-
JSGS: JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views
2026-08-09 12:05:34Jinhua Cui, Anhong Wang, Kai Hu, Donghan Bu, Peihao Li, Tammam Tillo, Hao Jing, Shiao XuAbstract
Standard 3D Gaussian Splatting (3DGS) assumes that every input image faithfully samples scene radiance. However, mixed-quality JPEG images violate this assumption because compression-induced blocking and ringing artifacts can corrupt updates to Gaussians shared across views. To address this problem, we propose JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views (JSGS). JSGS uses luminance and chrominance quantization tables stored in each JPEG file to construct a view-specific JPEG observation operator. This operator encodes and decodes each rendered view for domain-matched comparison with the corresponding decoded input image. The luminance quantization table supplies continuous weights within a fixed middle frequency band. A loss in the low frequency band anchors coarse structure, while the weighted middle frequency loss redistributes supervision among the selected DCT coordinates. The resulting block disagreement also guides the Gaussian Controller to regularize small primitives with high opacity in disagreement regions. Across seven scenes and three mixed-quality schedules, JSGS achieves the lowest mean LPIPS and the highest mean SSIM under every schedule while rendering at approximately 150 FPS. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08659
PDF
-
Hidden Language Consistency Phenomena in Reasoning LLMs
2026-08-09 03:30:14Muhammad Ali Shafique, Kelly MarchisioAbstract
Multilingual reasoning models are commonly evaluated by whether they arrive at the correct answer, but not by whether they preserve the intended language while reasoning and responding. This omission conceals important multilingual behaviors that emerge as tasks become harder. In this paper, we study task difficulty, task accuracy, thinking-language consistency (TC), and answer-language consistency (AC) across reasoning models using PolyMath benchmark in eight languages and four difficulty levels. We uncover four findings: (1) language consistency exhibits four difficulty-dependent behaviors: output-language consistency remains aligned with input, remains misaligned, degrades gradually, or collapses abruptly. (2) We identify the language consistency breakdown effect, where increasing difficulty can cause a sudden drop in output-language consistency, especially in less strongly represented and non-Latin-script languages. (3) Due to this breakdown effect, accuracy can be preserved or even improved at a harder difficulty level as the model shifts to its internal dominant language. (4) Quantization can improve or degrade output-language consistency independently of its effect on accuracy, with GPTQ and AWQ often outperforming AutoRound under tolerance-based voting with {\epsilon} = 1.0. These results show that multilingual capability cannot be characterized by accuracy alone; reliable evaluation should jointly consider task accuracy, language consistency, and task difficulty for multilingual benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08447
PDF
-
ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure
2026-08-08 18:35:10Zixiang Wan, Xusheng Yang, Zheng Wang, Peiji YangAbstract
Neural speech codecs face a fundamental tension in the language-model era: tokens that support high-fidelity reconstruction are not necessarily easy for autoregressive models to predict. Our controlled analysis of diverse codec and self-supervised speech representations shows that clearer phoneme structure before discrete code assignment is consistently associated with easier autoregressive token prediction. Yet phoneme structure alone is insufficient for high-fidelity reconstruction, which also requires reconstruction-relevant acoustic detail. Guided by this observation, we introduce ReLMCodec, a low-bitrate single-codebook speech codec built upon a preserve--control--refine principle: it preserves the linguistic organization of frozen self-supervised learning (SSL) features at the quantizer input, controls reconstruction-driven drift through Pre-quantization Anchor-Preserving Adaptation (PAPA), and refines the quantized latent space with a training-only WavLM-Large L24 teacher to reduce phoneme-level token fragmentation. Together, these components allow acoustic detail to support waveform reconstruction while keeping the resulting token sequence predictable for autoregressive models. At 650 and 800 bps, ReLMCodec moves the empirical single-stream predictability--reconstruction frontier in our evaluations, with gains that carry over to downstream text-to-speech (TTS) synthesis in both intelligibility and speaker similarity.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08286
PDF
-
Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification
2026-08-08 15:44:31Yutong Wu, Xiaofan Bai, Shixin Li, Pingyi Hu, Ziqi Zhou, Zilong Wang, Xiaojing Ma, Songfeng Lu, Yuhong Li, Jin Xuan, Yi Wang, Dongmei Zhang, Bin Benjamin ZhuAbstract
Large language models (LLMs) are high-value assets that can be derived through redeployment, fine-tuning, quantization, or further alignment. Because deployed LLMs are commonly exposed only through query APIs, ownership verification must often rely on black-box text responses. This setting is difficult: generations are open-ended and can vary across repeated queries, while existing black-box fingerprints rely on signals that are fragile under a final-response interface, including full-text matching, soft behavioral features, or model-specific prompts designed not to transfer. We propose TCF (Targeted Counterfactual Fingerprinting), a black-box LLM fingerprinting framework that converts open-ended generation comparison into constrained-answer targeted counterfactual transfer. TCF restricts each verification query to a finite answer space, reducing the surface-form ambiguity that enters the verification score, and optimizes a prompt perturbation toward a counterfactual target different from the protected model's clean answer on the original prompt. Verification reduces to checking whether the suspect model's parsed final answer matches the recorded target. We introduce the source-model counterfactual margin (SCM), a protected-model-only quantity that certifies the target is unlikely before the perturbation and likely after it; SCM controls target selection, perturbation stopping, and fingerprint filtering. Under explicit derived-preservation and independent-transfer budgets motivated by local behavioral closeness, we derive a target-accuracy gap between derived and independent models. Across four LLM families, TCF achieves an average AUC of 0.9861, improving over TRAP, ProFLingo, and ZeroPrint by 0.07 to 0.19.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08195
PDF
-
Quantization Degradation in Large Language Models: A Signal-Noise Perspective
2026-08-08 15:28:45Chenxi Zhou, Pengfei Cao, Jinyu Ye, Bohan Yu, Haida Yu, Jiang Li, Jun Zhao, Kang LiuAbstract
Post-training quantization reduces the deployment cost of large language models, yet how severely a quantized model degrades is not determined by bit-width alone. We systematically study weight-only post-training quantization across bit-widths, quantization methods, model scales and downstream tasks on multiple model families. We observe that such degradation varies substantially across these factors: 4-bit quantization usually preserves performance, 2-bit often causes broad degradation, and at 3-bit, degradation becomes apparent but varies markedly with task type, quantization method and model scale. To explain this variability, we use the signal-to-noise ratio (SNR) to measure how strongly quantization perturbs full-precision representations. We trace degradation back to two linked processes: how quantization errors arise within individual modules, and how they accumulate across layers. First, a source SNR decomposition shows that newly introduced errors depend on three factors: the magnitude of the weight error, the strength of the task-specific signal, and how strongly the quantization error aligns with task-specific activations. Different factors affect these components in distinct ways. Second, a cross-layer propagation analysis shows that these errors can be attenuated, preserved, or amplified as they pass across layers, and that larger models benefit from weaker error amplification. Together, these results establish that quantization degradation is governed by how errors are introduced at the source and how they accumulate across the network.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08188
PDF
-
TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance
2026-08-08 13:56:39Yuqi Wu, Shengming Zhao, Jie ChenAbstract
Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone cannot resolve. We introduce a training-free fingerprint based on the top-$k$ vocabulary projections of late hidden states elicited by 250 fixed knowledge probes, compared using Jaccard overlap over decoded token strings. We evaluate the method on 32 open-weight models from nine families (0.6B--32B) with documented relationships. (1)~A \emph{similarity ladder} broadly follows model relatedness: independently trained models on identical data score 0.48 raw (0.35 vocabulary-corrected), followed by shared-base fine-tunes (0.39/0.33), same-developer relatives (0.38/0.28), and models with no documented relationship (0.22/0.17). This identical-data signal persists across three organizations, two tokenizer families, and two architecture classes, and emerges within the first 1\% of training before measurable task competence, suggesting a contribution from shared training data beyond capability convergence. (2)~As a nearest-neighbor \emph{lineage-retrieval} method, the fingerprint ranks the exact documented base among the top two candidates for all five R1 distillations (mean rank 1.8, MRR 0.60), including a math-specialized base not identifiable from coarse metadata. (3)~A \emph{depth ablation} shows that lineage group discrimination strengthens toward the output distribution, with AUC increasing from 0.72 at quarter depth to 0.90 at the output; using only the top 5 output tokens retains AUC 0.87. (4)~The fingerprint remains stable under quantization, with Jaccard similarity of 0.92 under int8 and 0.82--0.85 under int4, compared with a maximum cross-model similarity of 0.81 in the calibration pool. We release the probes, code, and fingerprints.
Abstract (translated)
URL
https://arxiv.org/abs/2608.08139
PDF
-
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
2026-08-07 19:55:45Liad Gerstman, Aditya Dhakal, Dejan Milojicic, Avi MendelsonAbstract
Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems. However, as graph sizes grow, storing and processing them entirely on a single-node CPU-GPU system becomes increasingly impractical. A promising approach is to distribute the graph across multiple remote memory nodes, though this introduces a major bottleneck: inter-node network congestion during training. To address this, we propose LGNNIC, a novel inter-node system architecture that leverages SmartNICs co-located with remote memory nodes-a configuration already available in modern systems-to reduce communication overhead in distributed GNN training. LGNNIC offloads key preprocessing tasks to SmartNICs, reducing the volume of data transferred to computational (training) nodes and alleviating network congestion. We introduce two complementary techniques executed on the SmartNICs during the preprocessing phase: Neighbor Sampling, which performs mini-batch sampling, and Quantization of the sampled batches. To evaluate LGNNIC under different communication infrastructures, we designed both an optimized low-overhead DMA-based synchronization mechanism and a high-overhead socket-based alternative used as a benchmark. We evaluate the core SmartNIC offloading mechanisms across standard GNN workloads and sampling hyperparameters using a proof-of-concept (PoC) system comprising one remote-memory node with an NVIDIA BlueField-2 SmartNIC and one compute node with an A100 GPU. Both Neighbor Sampling and Quantization on the remote node demonstrated substantial training speedups in most configurations. Neighbor Sampling achieved up to 62.4x and 17.5x speedups with Sockets and DOCA-DMA, respectively, primarily due to reduced data transaction time. Quantization provided additional speedups of up to 3.6x and 1.3x, respectively, by reducing data transfer.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07733
PDF
-
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
2026-08-07 17:57:45Hanke Xie, Haopeng Lin, Jiale Qian, Dake Guo, Yuepeng Jiang, Zhichao Wang, Wenxiao Cao, Jingbin Hu, Guobin Ma, Wenhao Li, Huakang Chen, Chengyou Wang, Ming Tao, Zhonghua Fu, Lei Xie, Xinsheng WangAbstract
Continuous-latent autoregressive speech generation has emerged as a promising alternative to discrete-token modeling by avoiding quantization loss and preserving richer acoustic information. However, continuous acoustic targets do not ex- pose linguistic structure as explicit token-level prediction tar- gets. Consequently, the autoregressive language model (LM) must acquire linguistic structure indirectly through acous- tic prediction, which can compromise the content fidelity of generated speech. We propose SemBridge, a training-only semantic-token anchoring framework for continuous-latent autoregressive speech generation. SemBridge uses discrete se- mantic tokens to directly supervise autoregressive LM states and employs a Semantic-Aligned Acoustic VAE to organize the continuous target space under the same semantic refer- ence. The semantic supervision is used only during train- ing, while inference remains entirely continuous. We evalu- ate SemBridge on zero-shot text-to-speech (TTS) and score- conditioned singing voice synthesis (SVS). Across multi- ple benchmarks, SemBridge improves content accuracy, as measured by word and character error rates (WER/CER), while maintaining competitive speaker similarity and percep- tual quality. Experimental results demonstrate that explicit semantic-token supervision for autoregressive state learning is an effective and general direction for continuous speech generation. Speech samples are available.1 The model code and checkpoints will be available at this https URL lab/SemBridge
Abstract (translated)
URL
https://arxiv.org/abs/2608.07462
PDF
-
PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
2026-08-07 10:16:25Hui Xie, Tong Shi, Haotong Qin, Aishan Liu, Xiaode Liu, Jinyang GuoAbstract
Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization. Quantizing these states is challenging because their distributions differ across channels and from the preceding weights, while small perturbations near the firing threshold may alter spike decisions and accumulate over time. We propose PTQ4SNN, a membrane-aware post-training quantization framework that jointly quantizes weights and recurrent membrane states using only a small calibration set. First, a channel-wise Unified Scale Bridge constrains the membrane scale as s_mem,c = s_w,c * 2^k_c, adapting to membrane distributions while enabling shift-compatible scale conversion. Second, Mixed-Precision Bit Allocation assigns 2/4/8-bit precision to membrane channels according to firing activity and quantization sensitivity under an average-bit budget. The framework operates on reusable projection-LIF pairs and supports both convolutional SNNs and spike-driven Transformers without backbone retraining. Experiments on static and event-based classification and semantic segmentation show that PTQ4SNN effectively preserves model accuracy under W4 quantization and approximately 4-bit membrane precision.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07066
PDF
-
ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
2026-08-07 09:27:14Yongge Ma, Guoan Wang, Feiyu Wang, Yaoming Li, Qian Zhang, Zihan Yan, Yinjun Han, Tong YangAbstract
Post-training quantization (PTQ) is widely used to reduce the memory and computational cost of large language models. Existing PTQ methods typically obtain an initial quantized model through heuristic rules or greedy optimization, and once quantization is completed the resulting integer assignments are usually treated as final. This observation motivates a complementary optimization stage within PTQ that keeps quantized weights improvable after an executable quantized model has been produced, while preserving the quantized format. We introduce ReQuant, a backpropagation-free fixed-grid refinement procedure for this stage. Agnostic to the PTQ initializer, ReQuant takes an existing quantized model as a feasible starting point and iteratively revisits its discrete weight assignments on the fixed quantization grid. Accepted updates strictly reduce the mean squared reconstruction error and remain on the original grid. In this way, ReQuant turns the initially fixed PTQ output into an iteratively optimizable discrete solution and serves as a plug-and-play post-processing stage for existing PTQ pipelines. Experiments across diverse model families, bit-widths, and downstream tasks show that ReQuant consistently improves quantized models from heterogeneous PTQ initializers, with especially large gains on simple initializers and lower bit-widths. Notably, ReQuant can refine a simple round-to-nearest initialization across multiple sweeps until it approaches or surpasses GPTAQ under the same quantization format. These results establish ReQuant as a practical complementary stage for further improving existing PTQ pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2608.07019
PDF
