Quantization
-
Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects
2026-08-30 22:54:40Hongyu Yu, Yifei ShenAbstract
Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2608.30076
PDF
-
Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators
2026-08-30 18:37:46Armaan Singh, Ryan Trinh Le, Jasmine Kaur, Abdullah Sultan, Edward Lue Chee Lip, Kiran Nijjer, Adnan Ahmed, Vasu SharmaAbstract
Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior aligns more closely with explicit CoT or explicit no- CoT. Here, hidden CoT operationally denotes this neutral-prompt CoT-like alignment; HCDS does not directly observe or prove an unexposed reasoning trace. On GSM8K, HCDS is significantly positive for both Qwen3-4B variants (Thinking $+1.87$, $p = 1.2 \times 10^{-7}$; Instruct $+1.41$, $p = 1.9 \times 10^{-4}$), replicates across a different inference stack and quantization within $0.08$ ($+1.80$ and $+1.45$), and is not significantly positive in seven of eight length-adjusted calibration-control cells. The unadjusted score produces large positive scores on single-step arithmetic and numeric factual lookup. The variants also respond differently to no-CoT instructions: Instruct complies from the prompt alone, whereas Thinking continues reasoning and requires intervention. These findings show stronger, less prompt-conditional CoT-like behavior in the reasoning-tuned model, consistent with but not proof of latent reasoning. HCDS thus investigates latent reasoning without relying on models' self-reported traces.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29956
PDF
-
MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation
2026-08-30 16:40:32Xinyao Qin, Linxiang Peng, Youbao Ye, Di Yang, Jiangtao WangAbstract
Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approaches often rely on discrete quantization to discover action boundaries from motion representations. However, when spatial masking is introduced for representation learning, it can introduce representation ambiguity, while discrete quantization further amplifies small fluctuations in the latent space. The interaction between these two factors often leads to unstable code switching and severe temporal jitter near action this http URL address these limitations, we propose a novel Mask-aware Action Spatiotemporal Quantization (MASQ) framework. Our framework decouples the conflicting tasks of spatial feature inference and temporal this http URL the spatial dimension, we introduce a Joint-Level Structured Dropout (JLSD) mechanism that masks the entire temporal trajectory of selected joints, to encourage the model to learn discriminative inter-joint coordination patterns. In the temporal dimension, we design a mask-aware velocity loss that enforces motion consistency only on visible joints, that prevents gradient conflicts caused by masked signals and stabilizing temporal predictions. Extensive experiments on three widely used skeleton datasets, including HuGaDB, LARa, and BABEL, demonstrate that the proposed MASQ framework significantly outperforms existing state-of-the-art unsupervised methods. In particular, our model establishes a comprehensive and substantial leading advantage in the Mean over Frames accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.29891
PDF
-
OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization
2026-08-30 16:00:11Yishan Yao, Binjun Li, Hanling Yi, Pengyu Li, Xiaoqing Liu, Zihan Yang, Xiaotian Yu, Zhiwen YuAbstract
NVFP4 is an efficient microscaling format for low-bit inference, but activation outliers can still degrade quantization accuracy within NVFP4 blocks. Within each quantization block, large activations can dominate the block scale, increasing the quantization error of the remaining values sharing the same scale. Existing post-training quantization (PTQ) methods mitigate outlier errors through strategies such as mixed precision, rotation, or residual compensation, but these approaches are either not specifically tailored to NVFP4 or introduce additional computation. In this work, we revisit NVFP4 from a channel-grouping perspective and define the reducible error incurred by remaining block values under the scale set by the block maximum as Collateral Quantization Error. Based on this insight, we propose OCGQuant, a post-training quantization method centered on Outlier-Companion Grouping (OCG), which adaptively pairs outlier channels with low-magnitude companion channels to improve NVFP4 activation block composition. Experiments on Llama3 and Qwen3 show that OCGQuant achieves the lowest WikiText-2 perplexity and highest average downstream accuracy among evaluated PTQ methods, while maintaining prefill speedup close to RTN and matching its peak decoding memory. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00066
PDF
-
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
2026-08-30 06:30:31Qian Zhang, Yaoming Li, Zhewen Tan, Yanshu Wang, Heng Lu, Kun Su, Zongwei Lv, Wenhan Yu, Yongge Ma, Yinjun Han, Ruikuang Liu, Tong YangAbstract
Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ methods quantize each layer with a single closed-form second-order solver: to remain analytically tractable, they heavily approximate the global loss (dropping cross-channel coupling, pooling output rows into groups), and they then freeze the resulting Hessian across the entire layer, with no way to refresh it as the loss landscape shifts column by column--a phenomenon we call information misalignment. We propose REAL-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied after every column block (128 columns). By coupling this fine-grained correction with a sliding window mechanism for smooth cross-layer transitions, REAL-Q effectively mitigates error propagation across the network. On LLaMA-3.1 (8B and 70B) and Qwen3 (0.6B-32B) at W4A16, REAL-Q reduces end-to-end KL divergence by up to ~49% relative to state-of-the-art globally-guided methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.00049
PDF
-
SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference
2026-08-28 22:19:47Daeha Lee, Do-Hyung Kim, Jae-Hong KimAbstract
The key-value (KV) cache is the dominant memory bottleneck of long-context large language model (LLM) inference, growing linearly with context length. We show that uniform KV quantization on a fractional-bit grid does not degrade gracefully: under a prespecified multi-seed statistical protocol, Llama-3.1-8B-Instruct with an affine quantizer is statistically indistinguishable from FP16 KV down to 2.322 code bits/value and collapses at 2.0 bits - a quality cliff in (2.0, 2.322] that reappears in generation-time quantization and multi-turn dialogue and transfers to Mistral-7B. The cliff reframes importance-aware mixed precision: above it, eight model-internal importance indicators are statistically interchangeable, so the benefit of mixing is grid interpolation, reaching average precisions uniform quantization cannot realize. SemKV preserves every token, ranks tokens by a model-internal score, and assigns two adjacent above-cliff precisions, achieving a measured 6.0x storage reduction with no statistically detectable quality difference from full KV (n=900, three seeds), and outperforming FP16 token pruning granted a 1.5x larger memory budget. Replacing the affine base with a distortion-optimized quantizer (TurboQuant-MSE) lowers the cliff in every protocol tested, raising the no-detectable-loss operating point to 7.9x. The recipe: measure the cliff for the target deployment setting, then interpolate above it.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28911
PDF
-
SignRR: Retrieve and Refine Real Motion for Sign Language Production
2026-08-28 17:45:14Fidel Omar Tito Cruz, Angie Sanchez Marquina, Summy Farfan, Gissella BejaranoAbstract
Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainly follows two paradigms. Generative models synthesize motion from a learned prior or from noise, without reference to an observed signing instance, making rare hand configurations and signer-specific articulation difficult to preserve. Retrieval-based methods reuse real, well-articulated motion segments, but concatenating segments from different signers and co-articulation contexts can introduce rhythm and style inconsistencies across the full sequence, not only at segment boundaries. These limitations suggest a complementary solution: use retrieval to provide realistic articulation, and use learned refinement to impose the global coherence that retrieval alone lacks. We therefore propose retrieve-and-refine, a paradigm that starts from real retrieved motion and refines it into a globally coherent signing sequence rather than generating motion from scratch. Our framework, SignRR, initializes motion from a dictionary of real sign segments and refines the full sequence with a part-aware Residual VQ-VAE, where residual quantization preserves fine hand articulation and temporal length differences are handled in the latent space. Experiments on PHOENIX14T and CSL-Daily show that SignRR achieves state-of-the-art back-translation performance while maintaining competitive pose quality.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28568
PDF
-
H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference
2026-08-28 09:22:17Hao Yu, Zheng Li, Dayiheng Liu, Jianwei ZhangAbstract
The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language model (LLM) inference. NVFP4's micro-block design, such as a group size of 16, offers strong representational flexibility for capturing local weight distributions and isolating outliers, but it also introduces a large and highly sensitive space of per-group scaling factors. Existing post-training quantization (PTQ) methods primarily focus on refining quantized weight values, leaving this scale-selection step underexplored. To address this gap, we propose \textbf{H-Scale}, a lightweight post-processing method for NVFP4 per-group scale refinement. Instead of minimizing plain weight reconstruction error, H-Scale selects hardware-valid group scales using a diagonal second-order proxy derived from calibration activations, thereby targeting layer output perturbation more directly. It is designed as a drop-in replacement for RTN-style scale selection in diverse NVFP4 pipelines, requires only modest offline calibration, and introduces strictly zero overhead at inference time. Under a fixed evaluation protocol, experiments on mainstream LLMs show that H-Scale generally improves a broad range of NVFP4 baselines and brings several variants closer to the BF16 reference.
Abstract (translated)
URL
https://arxiv.org/abs/2608.28113
PDF
-
Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap
2026-08-27 08:34:10Jacopo Dardini, Claudio Stanzione, Giordano Col\`o, Giuseppe FenzaAbstract
Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent malicious payloads into models that satisfy the source-precision checks used in our evaluation, yet activate targeted adversarial behavior upon INT8 or 4-bit compression. We evaluate this threat in two operationally motivated scenarios, tactical machine translation and political content analysis, extending prior work from decoder-only causal LMs to multilingual encoder-decoder sequence-to-sequence models. Results show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization, and that a paired stance classifier measures an ideological shift of up to $\Delta\mathrm{Bias}=0.33$ upon compression. A cross-quantizer transferability analysis further shows that attack persistence varies across quantization schemes and model architectures, rather than being determined by nominal bit-width alone. These findings demonstrate that source-precision auditing alone does not rule out quantization-triggered behavior and that the final deployed configuration must be included in behavioral certification for trustworthy edge AI.
Abstract (translated)
URL
https://arxiv.org/abs/2608.27512
PDF
-
When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs
2026-08-26 16:32:50Yao Fu, Lijia Huang, Xiaomin Li, Runchao Li, Yu Yin, Kenneth A. LoparoAbstract
Personality is increasingly important in large language models (LLMs), as it shapes users' trust, engagement, and emotional experiences. While the Myers--Briggs Type Indicator (MBTI) has emerged as a common framework for assessing LLMs' personality, existing studies focus primarily on full-precision models and evaluate only final outputs. They overlook the widespread deployment of quantized LLMs requiring low memory footprints, whose personality traits remain underexplored. In this work, we present a systematic MBTI analysis of open-source LLMs across multiple precisions, including mainstream 4-bit methods (GPTQ, AWQ) and extreme 2-bit settings (AQLM variants). Beyond output-level evaluation, we examine how personality emerges across layers through option-level entropy and confidence-gap dynamics, and introduce Uncertainty-Amplified Layer Decoding (UALD) to study decoding-induced personality drift at inference time. Our results reveal a key insight: LLMs' personality is not a static property, but an emergent, layer-dependent decision process sensitive to quantization, prompting, and decoding. Specifically, we find that (1) ENFJ remains dominant across model families and precisions; (2) 4-bit quantization largely preserves coarse personality structure, while 2-bit quantization disrupts fine-grained prompt consistency and cross-precision agreement; (3) personality decisions emerges in upper layers, following substantial ambiguity in early layers; and (4) inference decoding can shift personality, while personality-aligned conditioning improves robustness. These findings provide a new perspective on the behavioral reliability of quantized LLMs and highlight the importance of considering internal dynamics and inference strategies in personality-sensitive chatbot applications.
Abstract (translated)
URL
https://arxiv.org/abs/2608.25977
PDF
-
Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization
2026-08-26 05:45:59Yefeng Yuan, Zhan Shi, Liang Cheng, Yuhong LiuAbstract
Multimodal synthetic datasets combine structured attributes with free text, but are often evaluated separately. Such metrics can remain high after tabular--text pairings are disrupted. We present a projection-based evaluator for tabular--text synthetic data. A fixed sentence encoder maps text to embeddings, \(k\)-means converts them to cluster states, and tabular variables are represented as categorical or quantile-binned states. Real and synthetic contingency tables are compared using Jensen--Shannon divergence (JSD), normalized mutual information (NMI), conditional JSD (cJSD), and joint-state entropy. We also report text-to-attribute (T2A) utility and a holdout-calibrated proximity flag rate (PFR) as a representation-level diagnostic. A text-permutation control preserves both marginal distributions while disrupting their pairing. Experiments on Amazon Reviews, Kiva Loans, and the Employment Scam Aegean Dataset show that modality-specific scores remain high under this control. The projection diagnostics detect disruption when real projected dependence exceeds a permutation baseline, but are less informative for weak or sparse projections. Some conditioned LLM baselines also exhibit stronger measured dependence than the corresponding real-data projections. These results support explicit cross-modal evaluation with permutation baselines and coverage reporting.
Abstract (translated)
URL
https://arxiv.org/abs/2609.22149
PDF
-
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
2026-08-25 16:18:52Zhehan Kan, Xinghua Jiang, Yubo Zhu, Yanlin Liu, Xiaochen Yang, Zhixiang Wei, Shifeng Liu, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing SunAbstract
Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervision. Existing efforts to introduce visual supervision typically do so during post-training, when visual representations have already been largely fixed, causing such signals to act mainly as auxiliary constraints rather than as a primary force for shaping perceptual features. In this paper, we aim to fundamentally reshape the model's perceptual backbone by incorporating vision supervision directly into the pre-training stage. We observe that pixel-level image patches and textual tokens naturally coexist in a shared, raw high-dimensional space characterized by an inherent input symmetry. Leveraging this insight, we propose UVU, a novel vision-language unified autoregressive framework that eschews vector quantization. It uniquely employs continuous visual encoding for lossless representation of visual inputs and proposes a large-scale iterative hierarchical clustering algorithm to construct a pixel-level visual codebook, thereby extending the vocabulary for unified supervision and enabling autoregressive generation of pixel-level image tokens alongside textual tokens. UVU effectively synergizes pixel-level visual perception with semantic-level visual understanding, internalizing visual reconstruction capabilities and unlocking the facilitative role of visual supervision in enhancing understanding in the pre-training stage. Extensive experiments across multiple tasks demonstrate that MLLMs are capable of achieving superior multimodal understanding performance under the supervised learning paradigm of UVU.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27915
PDF
-
Low-Rank Ternary Adaptation for Fine-Tuning Transformers
2026-08-25 12:15:56Alexandru-Dragos Manolache, Yunqiang Li, Jan van GemertAbstract
Ternary transformers offer extreme memory and compute efficiency, but existing low-bit LoRA-based methods cannot directly fine-tune ternary weights. Current approaches either require dequantization, restoring low-bit base weights to higher precision to merge with adaptation weight, or update only quantization parameters, preventing a merged model that remains ternary. We propose ternary multiplicative adaptation, which represents discrete updates of ternary weights such as sign flips or zeroing through a low-rank Kronecker factorization into two small ternary matrices applied element-wise to ternary weights. This design is parameter-efficient and expressive, preserves the ternary domain, and supports direct merging without dequantization. Experiments on six models across language and vision, including ternarized LLaMA-3 1B and 3B and a ternary ViT-B/16, demonstrate that our method recovers much of the performance lost to quantization and outperforms strong low-bit and ternary baselines. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24469
PDF
-
Tlow: Flow-based Item Tokenizer for Recommendation
2026-08-25 07:43:09Nian Li, Chonggang Song, Jingtao Ding, Lingling Yi, Yong Li, Qingmin LiaoAbstract
Item tokenizer encodes semantic embeddings into token IDs to replace the randomly assigned item IDs used in traditional recommendation models, fundamentally addressing the problems of excessive parameters and cold starts. However, the most common tokenizer, RQ-VAE, suffers from low decoding efficiency due to the inherent dependencies among its codebooks. Meanwhile, efficient independent tokenizers such as optimized product quantization (OPQ) still struggle with dimensional correlations and distribution complexity of semantic embeddings. In this work, we propose a f\underline{low}-based item \underline{T}okenizer (Tlow) to transform raw semantic embeddings into a latent space where embeddings conform to a unified standard normal distribution, achieving dual advantages of dimensional independence and distributional simplicity. Independent tokenization performed on these latent embeddings yields semantically clear token IDs. Additionally, we introduce a novel codebook guidance to align the codebook space with the token embedding space, further aiding the learning of more semantically distinct token embeddings. Offline experiments on four public datasets demonstrate that Tlow's tokenization and codebook guidance significantly improve recommendation performance. The improvement on cross-domain and multi-modal recommendations also proves the effectiveness of item tokenization in a simplified embedding space. Online experiments for a multi-modal retrieval task on China's largest social media platform WeChat validate Tlow's powerful distribution transformation capability. The retrieval model based on token IDs improves user CTR by 10.32\% globally and by 11.64\% for new items. Our codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24176
PDF
-
SandwichQuant: Which Parameters Matter Before and After Quantization?
2026-08-25 07:40:06Peng Xia, Junbiao PangAbstract
Quantization correction methods usually optimize weights, quantization parameters, or reconstruction objectives, while the underlying parameter subspaces responsible for effective correction remain unclear. In this work, we study quantization correction from a parameter subspace perspective and reveal that correction capability is highly non-uniform across parameter groups. By decomposing trainable parameters into backbone weights, normalization-affine parameters, and quantization parameters, we show that the low-dimensional normalization-affine subspace provides a highly efficient correction direction under matched budgets. Based on this finding, we propose SandwichQuant, a two-stage normalization-affine correction framework that performs adaptation before and after quantization. The pre-stage improves quantization robustness, while the post-stage compensates residual errors after the quantized graph is fixed. Extensive experiments on vision models and large language models demonstrate consistent improvements under various low-bit quantization settings, validating the effectiveness of subspace-aligned correction.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24173
PDF
-
Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LLM Compression
2026-08-25 05:09:07Mohammad MozaffariAbstract
Prohibitive computational and environmental costs impede the scalable deployment of Large Language Models (LLMs). Traditional compression techniques (sparsity, quantization, low-rank approximations) are typically applied in isolation, and each hits an accuracy-efficiency wall. This thesis proposes the "Compression Trinity," a unified framework that applies the three pillars jointly: sparsity to reduce computation, quantization to minimize memory bandwidth, and low-rank approximations to recover accuracy. To accelerate pretraining, we apply the Trinity to the optimizer and model architecture. MKOR approximates curvature via block-diagonal sparsity and low-rank inversion, maintaining numerical stability for quantized states; it reduces curvature update complexity from $O(d^3)$ to $O(d^2)$ and accelerates convergence by up to 1.85x over KFAC. SLoPe accelerates training by up to 1.25x via a double-pruned backward pass for N:M sparsity, using low-rank "lazy" adapters in the final 1% of training to recover accuracy. For post-training compression, OPTIMA stabilizes static masks in a zero-training regime by formulating weight reconstruction as globally optimal column-wise quadratic programs, improving zero-shot accuracy by up to 3.97%. Given a fine-tuning budget, PATCH breaks the ceiling of static masks by learning a dynamic hybrid sparsity ratio between 0% and 50%, yielding up to 1.38x speedups. Finally, SLiM realizes the full Compression Trinity in one shot, using mathematically derived low-rank adapters to recover information lost to quantization and sparsity, improving accuracy by up to 5.66% over state-of-the-art methods and outperforming uncompressed dense models at equal parameter budgets by 0.6%. Together, these results show that jointly applying the Compression Trinity is essential for efficient, scalable, high-performance LLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.24070
PDF
-
Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation
2026-08-24 14:04:35Chengqun Yang, Liang Xu, Yanping Li, Fulong Liu, Jingnan Gao, Weili Zeng, Yichao YanAbstract
Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For representation, Vector Quantization (VQ)-based methods compress motion data into discrete tokens while latent-based models operate directly in continuous space. However, both of these representations exhibit significant limitations. VQ-based methods suffer from inherent information loss, which compromises the quality, diversity, and generalization of generated motions, while continuous representation on holistic whole-body motion hinders part-level flexibility. For architecture, diffusion and autoregressive diffusion models have demonstrated their superiority, yet the fine-grained controllability over individual body parts is also limited. Thus, we propose a unified spatiotemporally decoupled framework named DeMoDiff, which jointly redesigns representation and architecture. To enhance representation extraction capabilities and offer greater part-level controllability, we present a spatial-temporal VAE that encodes each body joint rather than compressing the whole-body motion into a single latent space. Then, we incorporate spatial-temporal masking and attention mechanisms into an autoregressive diffusion generator, achieving both generative capability and controllable editability. Extensive experiments on the HumanML3D and KIT-ML datasets demonstrate that our model achieves state-of-the-art reconstruction performance and compelling motion generation results. Moreover, our framework demonstrates strong temporal and spatial editing capabilities, further validating its effectiveness. Our project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.23279
PDF
-
Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair
2026-08-24 11:49:37Zehao Liu, Chuangchuang Fang, Yang RenAbstract
Low-bit weight quantization saves storage but leaves errors that degrade language-model quality. We introduce Activation-Weighted Seeded Residual Coding (AWSRC), a compact repair codec for an existing quantization backbone. Given a reconstructed weight $W_0$, AWSRC encodes the residual $W-W_0$ using deterministic seed-generated bases. The sidecar stores seed selectors, low-bit coefficients, and scales rather than an explicit codebook. Activation statistics prioritize errors that affect layer outputs. On Qwen2.5-3B-Instruct, adding 0.162 scope-bits/weight to an INT4 RTN backbone closes 88.2%, 78.9%, and 71.3% of the matched PPL, KL, and accuracy gaps to BF16. Repairing a matched strong low-bit backbone also improves all measured quality metrics. With a matched 49.25 MB sidecar, about 0.8% of the BF16 model-weight payload, AWSRC gives the best perplexity and mean task accuracy among sparse, low-rank, and vector-quantized codecs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.23144
PDF
-
CSymPlan: Certified Symbolic Planning and Control for High-DOF Manipulators
2026-08-24 08:45:37Aditya Narendra, Ashok Kumar Saini, Mahathi Anand, Mahmoud Khaled, Fares J. Abu-Dakka, Abdalla SwikirAbstract
Robot manipulators are commonly engineered around a decoupled motion-generation stack: a planner computes a collision-free path and a lower-level controller tracks the resulting reference. This separation is computationally convenient, but it can produce references that are difficult to execute under actuator limits, tracking error, model mismatch, and small obstacle clearances. We present CSymPlan, a certified symbolic planning and control framework for high-DOF manipulators with two complementary implementations: an offline implementation that precomputes certified reach-avoid feedback policies for known workspaces; and an online implementation that synthesizes or updates symbolic policies at runtime from changing task and perception information using parallelization. The offline implementation reduces the manipulator dynamics to a sampled perturbed double-integrator model in operational space through feedback linearization, treats torque-realization errors, modeling inaccuracies, and measurement uncertainty as bounded disturbances, and refines the synthesized symbolic policy to the Franka FR3 through a quantization--lookup--torque realization pipeline. The online implementation uses the same abstraction and refinement interface, but replaces the precomputed policy table with a runtime pFaces request--synthesis--execution loop. In randomized simulated benchmarks and perception-driven Franka FR3 experiments, both implementations complete reach-avoid tasks with zero safety violations; whenever no certified action exists, the robot holds, replans, or stops safely instead of executing an uncertified command.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22983
PDF
-
SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems
2026-08-24 08:39:36Xiang Wang, Shigang Quan, Tingzhen Chang, Kang Yang, Sitong Chen, Yabo Fan, Xingxing Wang, Zhaodian HeAbstract
Deploying high-dimensional multimodal features in industrial recommender systems incurs substantial storage and latency overhead. Hard quantization is compact but introduces boundary distortion, whereas dense soft quantization couples representation quality to the limited storage budget. We propose Sparse Activation-based Residual Soft Quantization (SA-RSQ), which uses Top-K sparse routing and softmax weights to store compact (Index, Probability) tuples. The stored tuples decouple per-item storage from codebook dimensionality; for a fixed selected support, gradients propagate through the routing weights and weighted reconstruction without relying on a straight-through estimator. Experiments on a proprietary food-delivery advertising dataset show favorable reconstruction-performance and CTR trade-offs across storage budgets of 8-48 bytes per item. A preliminary Next-Distribution Prediction study and a one-week online A/B test further demonstrate the practical potential of SA-RSQ, with relative lifts of +2.51% in CTR and +3.66% in CPM.
Abstract (translated)
URL
https://arxiv.org/abs/2608.22979
PDF
