Quantization
-
Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions
2026-09-04 16:40:06Mahadev Sunil Kumar, Bhavika Gondi, Desaisetty Venkata Satya Sai Swapnith, Gangireddy Rahul Jogi, Sudheesh Manalil, Arnab Raha, Amitava Mukherjee, Parthasarathy Seethapathy, G. GopakumarAbstract
Chilli (Capsicum annuum) is one of India's most economically significant crops, yet its productivity is persistently threatened by diseases that are difficult to identify without expert intervention. While Vision Transformers (ViTs) have achieved high classification accuracy, their large computational footprint makes deployment on resource constrained devices challenging. Existing compression approaches typically address pruning, quantization, and knowledge distillation in isolation, leaving the potential benefits and interactions of their combined application insufficiently explored. We propose a unified Vision Transformer compression framework that combines Hessian-Balanced Adaptive Block Pruning (H-BAC), guided by second-order sensitivity estimation, with quantization and attention-based knowledge distillation. To systematically identify the most effective configuration within each compression family, each technique is first evaluated independently through controlled ablation studies, after which the best-performing components are integrated into a sequential deployment pipeline tailored to real-world agricultural constraints. On a chilli 3-class village-split dataset with a genuine cross-village, cross-device out-of-distribution test split, the resulting compressed models match or exceed the 95.13% FP32 baseline's accuracy, alongside 74-98% model size reduction, and the fully integrated compression pipeline achieves a 54.5x size reduction (327.42 MB to 6.01 MB) at 95.13 +/- 2.32% accuracy across four tested configurations. A direct comparison further reveals that, on this dataset, a directly-trained student of the same final size, without pruning or distillation, reaches comparable accuracy of 94.87%, at the same 6.01 MB INT8 size, indicating where H-BAC and knowledge distillation are, and are not yet shown to be, worth their computational cost.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05334
PDF
-
APEX-RBD: Mixed-Precision Exploration Framework for Hardware-Efficient Robot Dynamics Accelerator Design
2026-09-04 14:02:44Xingyu Liu, Hanwei Fan, Chaofang Ma, Jiawei Liang, Guangyu Hu, Jiang Xu, Wei ZhangAbstract
Rigid Body Dynamics (RBD) forms the computational core of real-time robotic control, but its immense computational complexity creates a performance bottleneck that necessitates dedicated hardware accelerators. However, the substantial hardware resource and power costs of these accelerators make their deployment on resource-constrained edge platforms highly challenging. While quantization offers a promising path to optimize RBD hardware for edge computing, existing uniform-precision approaches remain inefficient by ignoring the diverse quantization sensitivities of different variables. Although mixed-precision offers a superior alternative, its exploration is intractable due to a vast search space and the prohibitive cost of closed-loop simulation for motion accuracy evaluation. To address these challenges, we introduce APEX-RBD, an automated framework that makes mixed-precision exploration computationally tractable while effectively identifying hardware-efficient configurations. Specifically, it performs physics-driven search space pruning via variable grouping and sensitivity analysis, and employs a data-efficient, prior-informed surrogate model to enable rapid trajectory error prediction. This formulation guides a hybrid optimizer to identify area- and power-efficient designs under user-defined accuracy and performance constraints. Experimental results demonstrate that APEX-RBD discovers designs achieving up to 1.9$\times$ area reduction and 1.8$\times$ power savings compared to uniform-precision baselines across diverse robotic platforms.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05161
PDF
-
ProLombard: Structured Multi-Scale Modeling for Normal-to-Lombard Speech Conversion
2026-09-04 07:31:25Hongyang Chen, Xinmeng Xu, Youqiang Zheng, Xingyu Liu, Yuhong Yang, Zhongyuan Wang, Weiping Tu, Song LinAbstract
Normal-to-Lombard (N2L) speech conversion aims to improve speech intelligibility in noisy environments by transforming normal speech into Lombard-style speech while preserving linguistic content, speaker identity, and speech quality. Despite recent progress, existing methods typically model the Lombard effect at the utterance level or the frame level, overlooking its hierarchical nature and its entanglement with both speaker identity and phoneme-level content. This limitation leads to Lombard leakage in speaker representations and incomplete separation between Lombard characteristics and linguistic content. In this work, we propose ProLombard, a structured multi-scale N2L framework that explicitly models the Lombard effect across utterance-, phoneme-, and frame-level representations. To address Lombard-speaker entanglement, we introduce an aligned speaker encoder (ASE) that suppresses Lombard leakage by aligning Lombard-speech speaker embeddings with their normal-speech counterparts. To achieve more complete Lombard-content disentanglement, we develop a phoneme-aware disentanglement and injection mechanism that extends conventional frame-level modeling to the phoneme level. Furthermore, we design a vector quantization (VQ)-median module that provides robust phoneme-level representations through VQ-based segmentation and median-frame-based aggregation. Extensive experiments on Mandarin and English Lombard datasets demonstrate that the proposed approach consistently improves speech intelligibility, Lombard similarity, and perceptual quality over baselines while maintaining speaker identity. These results highlight the importance of structured multi-scale modeling for effective N2L speech conversion.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04828
PDF
-
Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs
2026-09-03 22:29:37Tung-Ling Li, Jiale Huang, Lee-Chi Wang, Janaki Ram GoteiAbstract
Merging a LoRA adapter into its base model is standard deployment practice: it removes the runtime adapter's per-forward overhead and leaves a single standalone checkpoint any serving stack can load. On a native 4-bit microscaling checkpoint (NVFP4, MXFP4) that step stops being free. The merged weights must be written back through a quantizer, which re-derives the checkpoint's discrete E2M1 code plane (roughly 90% of the artifact's bytes), so the deployed artifact becomes coupled to one quantization convention, and every later code-touching event in its lifecycle can move it. Done naively the step is worse than fragile: it deletes the adaptation, by up to 39 pp, because against an already-on-grid base the reconstruction optimum is that base. Scale-QLoRA instead adapts only the native per-block scale field, trains those scales on the deployment grid, and freezes every E2M1 code. Within a fixed native format, scale grid, block layout and code plane, merging is then a bit-exact identity and the merged artifact is code-invariant. Across four models and four tasks, Scale-QLoRA and merge-aware QAT-LoRA are both accuracy-lossless, so we claim no accuracy ordering between them; they differ structurally, in that QAT-LoRA re-derives the code plane through a quantizer while Scale-QLoRA preserves it exactly. That difference is what the lifecycle prices: nearest-rounding implementations disagree by about a point on the measured task, and more extreme rule mismatches can drive the weight-space artifact to ~0%, which we report as a sensitivity bound rather than a deployment frequency. Preserving the code plane also drops the weight-space straight-through estimator from training (3.9x per step on the dense 8B model) and enables exact rollback, code-plane deduplication, and a ~125x faster scale-only task swap.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04526
PDF
-
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference
2026-09-03 21:23:35Ismail Erbas, Xavier Intes, Vikas PandeyAbstract
Quantization is widely used to reduce the computational and memory demands of neural-network inference. In recurrent networks, however, the quantized state is stored and returned at the next time step, so the rule used to store that state can alter subsequent computations. Here, we introduce recurrent-state write-back to denote this rule and isolate its effect in a compact GRU encoder--decoder for fluorescence lifetime imaging, a molecular imaging modality used in quantitative biological imaging. A central task is estimating two lifetime parameters, the short-lived component {\tau}1 and the long-lived component {\tau}2, from high-noise time-resolved fluorescence signals. Holding the trained model fixed, replacing continuous state propagation with deterministic 4-bit state storage increases estimation errors for {\tau}1 and {\tau}2 by approximately 70x and 300x, respectively. Failure occurs when repeated small updates remain below the write threshold, leaving the stored state nearly fixed while the network continues to propose change. Error feedback, residual memory, and direction memory carry information from these suppressed updates across time and recover accuracy without retraining. Precision sweeps show that increasing state precision can worsen a fixed recurrent solution, while matched training shows that compatibility with the state interface can be learned. To test whether this behavior extends beyond the GRU, we repeat the post-training intervention in an independently trained LSTM, where coarse write-back reproduces the failure, error feedback restores accuracy, and state-specific interventions reveal greater sensitivity of the cell state than the hidden state. Our results establish recurrent-state write-back as a key determinant of low-precision recurrent dynamics and identify the state-storage interface as a central design consideration for quantized recurrent inference.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04490
PDF
-
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
2026-09-03 17:04:26Sergii Kozyrev, Davyd MaiborodaAbstract
Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially its decay and write-strength gates -- on the intuition that errors in a recurrence accumulate over long contexts. We test that intuition by building Minima: NVFP4 W4A4 on all 496 linear layers, GDN included. Across perplexity at 4K/32K, MMLU-Pro, GSM8K, AIME'25, GPQA-Diamond, LiveCodeBench, and RULER retrieval to 64K, Minima matches BF16 within seed noise (5-task average -0.52) while being the smallest (17.5 GiB) and fastest-prefill (+14-19%) recipe we compare, and its 32K perplexity gap shrinks with position. A four-part mechanism study explains why: (i) NVFP4's 16-element block scaling localizes the residual stream's extreme outliers, equalizing activation error across layer roles; (ii) the supposedly fragile gate projections are the least sensitive -- softplus/exponential and sigmoid parameterizations compress ~11% GEMM error to ~2% output error; (iii) the delta-rule recurrence holds injected noise at a flat plateau over 32K tokens and forgets a state impulse within hundreds of steps, because each write overwrites the state along the current key direction; (iv) the per-token quantization cost washes out with context instead of compounding. We also repair a global-scale mismatch that arises when per-module-calibrated NVFP4 checkpoints are served by kernels that fuse those modules into one GEMM, and show calibrated FP8 KV-cache scales are performance-free. The result: a practical recipe -- quantize everything, ship KV scales -- and a mechanistic account of why the recurrent half of a hybrid LLM is the easy half to quantize. Checkpoint: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.04098
PDF
-
Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving
2026-09-03 16:42:11Ruoyu Yao, Yusen Xie, Qingzhao Liu, Pei Liu, Zewei Yang, Yipeng Zhu, Xiaolong Wang, Jun MaAbstract
Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a significant challenge. In this work, we introduce LaPla, a unified Vision-Language-Action (VLA) framework featuring latent-aligned planning to seamlessly ground semantic understanding in precise motion execution. We first design an action tokenizer based on a residual vector-quantized variational autoencoder (VQ-VAE), capturing vehicle kinematics and encoding trajectory features into a structured latent space. Rather than discrete codebook lookups that inevitably introduce quantization errors, LaPla repurposes this representation as a physical prior to bridge the modality gap between high-dimensional semantics and the raw action space. Specifically, given multimodal inputs integrating multi-view images, historical actions, and textual instructions, LaPla incorporates concurrent action queries to causally attend to the multimodal context in a single forward pass, projecting hidden states directly into the pretrained VQ-VAE latent space. The frozen decoder then translates these continuous latents into actions, effectively eliminating quantization errors and ensuring physically plausible trajectories while bypassing time-consuming autoregressive generation. Extensive experiments on the nuScenes benchmark demonstrate that LaPla achieves competitive open-loop performance, reducing long-horizon L2 error by 15.52% compared to state-of-the-art VLA methods. Closed-loop evaluations on the NVIDIA AlpaSim simulator further confirm its superior capability in ensuring smooth driving progress, improving the success rate by 33.34 percentage points with significantly reduced inference latency.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04070
PDF
-
DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
2026-09-03 16:09:25Shuaiting Li, Zelin Gao, Haibin Shen, Yujun Shen, Haotong Qin, Yinghao XuAbstract
Video diffusion models (VDMs) have achieved impressive progress in text-to-video generation, but their high memory and computational costs hinder practical deployment. Quantization-aware training (QAT) is an effective solution for compressing and accelerating advanced generative models without runtime overhead at inference. However, existing QAT methods suffer from a distinctive challenge in VDMs: while they often preserve prompt semantics, global layout, and coarse motion, the quantized model severely degrades visual details, texture fidelity, and sharpness. In this paper, we trace this degradation to the timestep-agnostic design of conventional quantization pipelines, which overlooks the stage-wise functionality of video denoising. In VDMs, early denoising steps mainly establish global structure and motion, whereas middle and late steps refine local appearance and high-frequency details. Based on this insight, we propose DSAQuant, a Denoising-Stage-Aligned Quantization-aware training framework for VDMs. During training, Denoising-Stage Oriented Supervision preserves teacher distillation in early steps for stable structure planning, while shifting later steps toward target-driven optimization to enhance detail reconstruction. During inference, Denoising-Stage Gated Guidance disables CFG in the final denoising steps to prevent it from amplifying quantization-induced errors into high-frequency artifacts. Extensive experiments on the Wan and CogVideoX families under W4A4 and W3A3 settings show that DSAQuant consistently outperforms the SOTA QAT baseline, improving the VBench average score by up to 6.60 under aggressive W3A3 quantization while preserving strong text-video alignment. These results demonstrate that effective VDM quantization requires not only reducing quantization error, but also aligning quantization training and inference with the stage-wise nature of video diffusion.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04031
PDF
-
VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch
Abstract
The problem. A long-lived KV cache must be compressed before the queries that will read it exist; selection by observed attention (H2O, SnapKV) collapses there (0.00-0.33 needle retrieval on a NoPE MLA model), because a token's importance has not yet been observed. The method. On Kimi Linear, VestigeKV evicts by a query-independent signal the cache already carries: the 64-dimensional decoupled branch, a vestige of RoPE that NoPE training repurposes into a salience channel. Reading 11% of each row, it partitions the cache: the top-m rows stay in the attended tier; every other row moves -- exactly, never deleted -- to a GPU-resident archive reachable per step by a certified trigger. No training, no quantization, no weight or kernel change. Cost. Nothing measurable: retrieval holds at 1.00 under 8x and 0.92 under 32x from 8k to 65k context, zero gap to full-row selection. The attended tier is 0.25 KB of Kimi Linear's 8.1 KB per-token cache at 32x; the archive stays bit-exact and GPU-resident, with host offload as the VRAM-reclaiming variant. The recall tier -- the standard configuration -- holds 128x at 1.00. Kimi K3 is reported to use a NoPE Gated-MLA variant; if its cache layout matches, the method plausibly extends there -- we make no claim beyond the measured model. NoPE exclusivity. The identical operator on a RoPE MLA collapses to 0.08 (plain eviction: 0.42); query-independent salience itself exists only without rotation (top-1 targets span 2.3-6.7% of tokens vs. 10.2-46.8%), and query-universal exact merging is provably impossible under RoPE. All thresholds were frozen before data; 20 archived verdicts and 8 closed routes accompany the paper.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03949
PDF
-
Tree-Structured Vector Quantization For Efficient And Progressive Image Compression
2026-09-03 10:41:36Xinkun Wang, Tianyi Xu, Qingyu Luo, Mingming Ma, Changzhe Jiao, Fu Li, Yi NiuAbstract
Vector-quantization based image compression has achieved strong rate--distortion performance, yet most of them still produce a separate compressed representation for each target bitrate. Such variable-rate behavior allows one model to operate at multiple rates, but it does not necessarily provide a progressive bitstream whose prefixes are themselves decodable and can be refined by appending additional bits. We propose \textbf{Tree-VQ}, a progressive tree-structured vector quantization framework for learned image compression. Tree-VQ organizes discrete codewords as a hierarchical binary tree and represents each latent token by a routed root-to-leaf path. Crucially, every prefix of this path corresponds to a valid quantized representation, so shallow internal nodes serve as coarse reconstruction codes and deeper nodes provide successive refinements. This allows a compressed image to be decoded from an early prefix and progressively improved as more branch symbols are received, rather than being re-encoded for different target rates. To make this structure practical for compression, we introduce a prefix-compatible tree entropy model that codes progressive continuation decisions and routed branch refinements using only causally available decoded contexts. We further use rate-aware refinement scheduling to decide which spatial blocks should receive additional tree bits under a given prefix budget, and hierarchical prefix supervision to ensure that internal nodes are directly decodable at low rates. Experiments show that Tree-VQ achieves a superior performance--efficiency trade-off, delivering the best perceptual compression results with much fewer parameters and lower latency than competing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03641
PDF
-
PACodec: A Low-bitrate Neural Speech Codec with Parallel Additive Vector Quantization
2026-09-03 04:40:28Fei Liu, Yang Ai, Xiao-Hang Jiang, Zhen-Hua LingAbstract
This paper proposes PACodec, a novel low-bitrate neural speech codec based on parallel additive vector quantization (PAVQ). Unlike the mainstream residual vector quantization (RVQ) used in most neural speech codecs, where vector quantizers (VQs) are sequentially dependent, the PAVQ strategy adopted in PACodec aggregates parallel quantization results to optimize bitrate usage. Specifically, the PAVQ adopts a "global-local-global" (GLG) design: the global encoded features are quantized in parallel by multiple independent VQs, each attending to a local component of the representation, and their outputs are aggregated through addition to yield the final global quantization result for decoding. Experimental results show that PACodec, as each VQ focuses only on local information, supports smaller codebooks and reduces bitrate by 30% compared with baselines at the same decoding quality, with only minor model complexity. Further analysis shows that, owing to the GLG framework of PAVQ, the proposed PACodec is disentanglement-friendly, and each independent VQ captures different aspects of speech, e.g., content, timbre, and acoustic details, suggesting potential for application to downstream tasks such as voice conversion.
Abstract (translated)
URL
https://arxiv.org/abs/2609.03363
PDF
-
Multi-scale Image Representation Compression
2026-09-02 21:44:26Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David BullAbstract
Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at the cost of a longer overfitting process. However, these overfitted image codecs are not fully optimized toward the rate-distortion objective: their network weights remain in full precision during training, and the associated quantization parameters are selected in a separate post-training stage. Furthermore, their synthesis operates at a single scale, which overlooks cross-scale redundancy. In this paper, we propose MIRC, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC. We further introduce a multi-scale representation with cross-stage parameter sharing, which improves coding efficiency at a small transmitted overhead. On the CLIC2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0). Moreover, MIRC offers a family of configurations spanning 1.2 to 2.9 kMAC per pixel, so the decoding budget can be selected to match the deployment target.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04274
PDF
-
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
2026-09-02 16:14:48Jitai Hao, Ke Yang, Qiang Huang, Jun YuAbstract
Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and early warning, and wearable assistants. However, processing continuous video streams with multimodal large language models (MLLMs) is computationally expensive. Existing efforts have explored reducing streaming overhead through visual token pruning, token merging, quantization, on-demand frame retrieval, and context offloading. However, most existing methods overlook the dimension of model depth. Repeatedly executing full-depth MLLM prefill over incoming frames is prohibitively expensive, incurring substantial computational overhead and causing the KV cache to grow at a rate directly proportional to the prefill depth. To address these challenges, we propose ShallowStream, a novel framework that leverages the shallow layers of an MLLM to simultaneously perform frame encoding and retrieval index building. During stream processing, ShallowStream maintains an always-on lightweight index using the KV cache of shallow layers. During query-time answering, we leverage the attention scores generated by the shallow layers to score context frames and employ a diversity-aware selection strategy to retrieve precise and comprehensive evidence. ShallowStream achieves performance on par with the strongest existing streaming methods, while reducing per-frame prefill latency and 10-second end-to-end latency by up to 52.1x and 11.9x, respectively. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02780
PDF
-
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
2026-09-02 12:01:54Irina Proskurina, Guillaume Metzler, Antoine Gourru, Julien VelcinAbstract
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying significantly depending on persona cues in the prompt. In this paper, we introduce Debias-SparseGPT, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs. We perform empirical validation of our method over a wide range of generative LLMs. Across models and sparsity regimes (25%, 50%, and structured 2:4 sparsity), Debias-SparseGPT consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy. Under the most restrictive 2:4 structured sparsity pattern, which most aggressively degrades model quality, augmenting the calibration set with long-context, content-rich examples further improves both downstream performance and fairness. Overall, Debias-SparseGPT advances the bias-performance trade-off while preserving the computational efficiency of sparse models.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02496
PDF
-
Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression
2026-09-02 11:17:52Viacheslav Yusupov, Daria Cherniuk, Evgeny FrolovAbstract
In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer interactions without storing the entire Fisher matrix, enabling practical Hessian analysis for billion-parameter networks where full computation is infeasible. Our approach reveals consistent vulnerability patterns: value projection layers exhibit the highest sensitivity and strongest cross-layer correlations across multiple model families, while other components exhibit architecture-specific behaviors. Through extensive experiments on quantization, sparsification, inter-layer corruption, and post-corruption fine-tuning, we demonstrate that our approximation strongly correlates with both performance degradation and recovery. Our framework provides a practical, theoretically grounded tool for identifying fragile components in large models, opening new avenues for guided compression and optimization strategies, such as mixed-precision allocation, layer-wise sparsity, and adaptive low-rank decomposition across layers and even individual weight groups.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02451
PDF
-
The Effect of Quantization on Clinical Benchmarks: Accuracy and Safety Across Model Families
2026-09-02 08:18:53Leonard Twagirayezu, Prasenjit MitraAbstract
Quantization enables deployment of large language models on resource-constrained clinical edge devices, but its effect on clinical accuracy and safety remains understudied. We evaluate five 7-8B parameter models at FP16, GPTQ-INT8, and GPTQ-INT4 precision across five benchmarks: MedQA, MedMCQA, Med-HALT, a risk-stratified sample of HealthBench, and MedSafetyBench. The study jointly varies quantization bit width, model family, and clinical task type, with explicit risk stratification and safety measures. INT8 GPTQ is universally safe (max. degradation -1.9%-1.9%), while INT4 degradation is substantial and model-dependent: BioMistral-7B, clinically fine-tuned, loses 19.7% on MedMCQA, more than any general-purpose model, showing clinical fine-tuning does not confer compression robustness. MedMCQA degrades more than MedQA under INT4; Med-HALT is largely unaffected. On HealthBench's emergency-risk subgroup, Qwen2.5-7B degrades by 26.8% under INT4, suggesting high-risk scenarios are disproportionately vulnerable to compression. On MedSafetyBench, the model family dominates over precision (refusal rates range 10.2%-74.9% at FP16), though Qwen2.5-7B (-17.8%) and Meditron-7B (-28.3%) show substantial INT4 safety degradation; notably, Qwen2.5-7B is simultaneously the most accuracy-robust model, demonstrating that accuracy and safety robustness are independent properties. We additionally test two recovery methods, clinical calibration substitution and QLoRA fine-tuning, both producing the same trade-off: MedMCQA recovers while MedQA further degrades, indicating recovery strategies require task-specific validation rather than being assumed universally beneficial. These findings indicate INT8 is broadly safe for clinical deployment, while INT4 safety must be assessed per-model and per-task, and that safety alignment is determined primarily by instruction tuning rather than clinical domain adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22216
PDF
-
Hardware-Accelerated Instance Segmentation for Resource-Constrained Space Robotics with Criticality Analysis
2026-09-02 07:33:27Siddhant Shete, Hilmi Dogu K\"uc\"uker, Udo Frese, Frank KirchnerAbstract
Autonomous lunar missions require real-time per- ception under three coupled constraints: extreme low-light conditions, limited onboard compute, and radiation-induced hardware faults that can silently corrupt inference. We present a deployment-oriented instance segmentation framework for resource-constrained lunar robotics that jointly addresses quan- tization calibration and system-level fault exposure under strict compute constraints. First, we introduce Activation Variance Informative Sampling (AVIS), a label-free calibration strategy that deterministically selects calibration samples based on activation variance statistics. Second, we deploy a YOLO-based segmentation model on a Deep Learning Processor Unit (DPU) with architectural modifications that reduce CPU fallback paths and enable statically compiled execution with bounded latency in low-lighting conditions. We further introduce a software-level criticality analysis to estimate fault exposure and guide mitigation under radiation-constrained operation. On a lunar micro-rover platform, AVIS with bias correction recovers 69.8% of quantization-induced accuracy loss while achieving 309 ms inference latency and 5.7 W power consumption. Targeted mitigation reduces global criticality by 31.7%. The results demonstrate an integrated approach and a blueprint for a reliable and safe AI perception framework under space deployment constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02219
PDF
-
CC-4DGS: Computational Deformation and Point-Cloud Compression for Storage-Efficient Dynamic Gaussian Splatting
2026-09-02 06:47:19Kyungdae Park, Chae Eun RheeAbstract
Dynamic four-dimensional (4D) Gaussian Splatting has emerged as a powerful explicit representation for high-quality view synthesis, yet existing methods still require tens to hundreds of megabytes per scene due to their heavy reliance on large multi-resolution hash tables and high-dimensional Gaussian attributes. This paper presents CC-4DGS, a storage-efficient and scalable framework that rethinks both deformation modeling and canonical attribute storage. First, we introduce a computational deformation field (CDF) that replaces large multi-resolution learnable hash tables with deterministic dense hash encoding and compact neural decoders, enabling on-the-fly synthesis of deformation features while reducing deformation storage to only 1--3 MB per scene. Second, we propose a compression of canonical point-cloud attributes (CCA) pipeline that compresses high-dimensional spherical harmonic appearance terms and auxiliary Gaussian attributes via conditional autoencoding, selective quantization, and residual codebooks, achieving 3--5$\times$ point-cloud reduction with negligible quality loss. Together, these components yield a unified representation that preserves real-time rendering performance while reducing total storage to 20--30 MB. Extensive experiments across the N3DV and Technicolor Light Field datasets demonstrate that CC-4DGS achieves reconstruction accuracy comparable to state-of-the-art methods such as Swift4D, while offering significantly improved storage efficiency and favorable runtime-memory trade-offs.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02184
PDF
-
A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization
2026-09-02 04:50:51Xianghong Fang, Wenlong Mou, Yuan Yuan, Dehan Kong, Tim G. J. RudnerAbstract
Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding quantization tradeoffs. In this paper, we propose a unified rate--distortion perspective on modern discrete visual tokenization. By viewing quantization as lossy compression, we characterize the nominal fixed-length coding rate through token count and codebook size, and quantization error as the distortion. Within this framework, we resolve three central questions. First, we theoretically and empirically show that minimizing distortion, rather than maximizing codebook utilization, is the primary intrinsic objective for reconstruction fidelity, with a direct connection to the STE-induced gradient discrepancy. Second, we establish two critical fairness conditions for intrinsic quantization comparison: controlling latent feature statistics and enforcing identical coding rates. Third, under these conditions, we recover the VQ--PQ--SQ distortion hierarchy in modern visual tokenization and show empirically that modern VQ methods achieve the lowest distortion. This work provides a foundational rate--distortion reframing of modern discrete visual tokenization, resolves ambiguities in quantizer evaluation, and provides a controlled framework for isolating intrinsic quantization effectiveness under fixed-rate constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2609.02107
PDF
-
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
2026-09-01 21:07:51Jundong Hu, Shekar RamachandranAbstract
Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet practitioner-defined thresholds and, when they fail, why, and whether quantization changes the answer. We build a benchmark of 4 such microtasks with fixed prompts and automatic metrics, each with a pre-specified threshold $\tau$ anchored to a cheap non-LLM baseline and a CI-aware eligibility rule (a configuration passes only if its confidence bound clears $\tau$). Sweeping Qwen3 0.6/1.7/4/8B at their best (FP16, greedy, one frozen prompt, no tuning), we find an eligibility gap: 0 of 16 (4 tasks $\times$ 4 models) configurations pass (verified by checking the raw outputs and parser behavior). A logprob decision-threshold diagnostic (T1/T3/T4; T2 via a context-length/cascade probe) separates the failures into capability deficits and failures that can be addressed by changing the decoding threshold (4 regimes). Quantization to 4-bit (RTN/GPTQ/AWQ) does damage that depends on model size and moves no configuration into eligibility (certified on the reconstructable hard-label tasks T1/T3, diagnostic/windowed robustness on T2/T4), so the gap tracks model size more than precision; it replicates on Llama-3.x (12/12 ineligible) and is robust to the anchor choice (a $\tau$-sweep) and to prompt wording (0/112 eligible across the original plus 3 neutral paraphrases per cell). The practical implication: place SLMs behind a baseline that meets the CI-backed threshold, and use the SLM only where the baseline fails to meet the threshold; e.g. a 4B re-ranker over a BM25 shortlist beats BM25 ($+0.047$ [0.020, 0.073], without itself certifying eligibility).
Abstract (translated)
URL
https://arxiv.org/abs/2610.00025
PDF
