Quantization
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
2026-05-14 17:58:03Haoyi Zhu, Haozhe Liu, Yuyang Zhao, Tian Ye, Junsong Chen, Jincheng Yu, Tong He, Song Han, Enze XieAbstract
We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p, minute-scale videos with precise camera control. SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention combines frame-wise Gated DeltaNet (GDN) with softmax attention for memory-efficient long-context modeling. (2) Dual-Branch Camera Control ensures precise 6-DoF trajectory adherence. (3) Two-Stage Generation Pipeline applies a long-video refiner to stage-1 outputs, improving quality and consistency across sequences. (4) Robust Annotation Pipeline extracts accurate metric-scale 6-DoF camera poses from public videos to yield high-quality, spatiotemporally consistent action labels. Driven by these designs, SANA-WMdemonstrates remarkable efficiency across data, training compute, and inference hardware: it uses only $\sim$213K public video clips with metric-scale pose supervision, completes training in 15 days on 64 H100s, and generates each 60s clip on a single GPU; its distilled variant can be deployed on a single RTX 5090 with NVFP4 quantization to denoise a 60s 720p clip in 34s. On our one-minute world-model benchmark, SANA-WM demonstrates stronger action-following accuracy than prior open-source baselines and achieves comparable visual quality at $36\times$ higher throughput for scalable world modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2605.15178
PDF
-
Widening the Gap: Exploiting LLM Quantization via Outlier Injection
2026-05-14 17:50:39Xiaohua Zhan, Kazuki Egashira, Robin Staab, Mark Vero, Martin VechevAbstract
LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existing quantization-conditioned attacks have been limited to relatively simple quantization methods, where the attacker can estimate weight regions that remain invariant under the target quantization. Notably, prior attacks have consistently failed to compromise more popular and sophisticated schemes, limiting their practical impact. In this work, we introduce the first quantization-conditioned attack that consistently induces malicious behavior that can be triggered by a broad range of advanced quantization techniques, including AWQ, GPTQ, and GGUF I-quants. Our attack exploits a simple property shared by many modern quantization methods: large outliers can cause other weights to be rounded to zero. Consequently, by injecting outliers into specific weight blocks, an adversary can therefore induce a targeted, predictable weight collapse in the model. This effect can be used to craft seemingly benign full-precision models that exhibit a wide range of malicious behaviors after quantization. Through extensive evaluation across three attack scenarios and LLMs, we show that our attack achieves high success rates against a broad range of quantization methods on which prior attacks fail. Our results demonstrate, for the first time, that the security risks of quantization are not restricted to simpler schemes but are broadly relevant across complex, widely-used quantization methods.
Abstract (translated)
URL
https://arxiv.org/abs/2605.15152
PDF
-
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
2026-05-14 17:44:10Saisab Sadhu, Pratinav Seth, Vinay Kumar SankarapuAbstract
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact but a systematic dual failure: gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model. Both failures trace to the same root cause: across all baselines, per-parameter updates lie 47-828x below the NF4 quantization bin width; updates diffused across billions of parameters cannot clear quantization bin boundaries, a consequence we formalize as a sparsity-permanence tradeoff. We present MANSU (Mechanistic-Aligned Null-Space Unlearning), which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph, circuit-restricted null-space projection with a diagonal-Fisher retain bound, and a per-parameter magnitude floor guaranteeing quantization survival by construction. We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression, a distinction existing metrics cannot make. Across multiple model families and hazard benchmarks, MANSU is the first method to jointly satisfy all four properties with margin on each (meaningful forgetting, retain preservation, non-positive PTQ gap, and structural erasure), while gradient-based baselines recover up to +0.05 accuracy under compression.
Abstract (translated)
URL
https://arxiv.org/abs/2605.15138
PDF
-
Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
2026-05-14 14:38:56Senne Deproost, Denis Steckelmacher, Ann Now\'eAbstract
Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simple class of model can be optimized using gradient descent. By exploiting the critic value network of the original policy, we iteratively introduce new subpolicies in regions with insufficient value, standing in for a measure of policy complexity. The partitioning, a Voronoi quantizer, uses nearest neighbor lookups to assign a linear function to each point in the state space resulting in a cell-like diagram. We validate our approach on several well known benchmarks and proof that this distillation approaches the original policy using a reasonable sized set of linear functions.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14897
PDF
-
Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
2026-05-14 14:35:51Isma Hadji, Enrique Sanchez, Adrian Bulat, Brais Martinez, Georgios TzimiropoulosAbstract
We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break image tokenization into additive, gradually increasing scales, using Residual Quantization (RQ), an approach that aligns perfectly with our target ISR task. Previous works taking advantage of this synergy suffer from two main shortcomings. First, due to the limitations in RQ, they only generate images at a predefined fixed scale, failing to map intermediate outputs to the corresponding image scales. They also rely on large backbones or a large corpus of annotated data to achieve better performance. To address both shortcomings, we introduce two novel components to the VAR training for ISR, aiming at increasing its flexibility and reducing its complexity. In particular, we introduce a) a \textbf{Hierarchical Image Tokenization (HIT)} approach that progressively represents images at different scales while enforcing token overlap across scales, and b) a \textbf{Direct Preference Optimization (DPO) regularization term} that, relying solely on the (LR,HR) pair, encourages the transformer to produce the latter over the former. Our proposed HIT acts as a strong inductive bias for the VAR training, resulting in a small model (300M params vs 1B params of VARSR), that achieves state-of-the-art results without external training data, and that delivers multi-scale outputs with a single forward pass.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14891
PDF
-
XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
2026-05-14 13:52:31Thomas WittAbstract
We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality floors on per-channel cosine similarity (one strict floor for attention and shared experts, one lazy floor for routed-expert MoE); XFP determines codebook size, outlier budget, and packing per layer automatically -- no Hessian, no calibration data, no manual bit-width selection. Each weight matrix is decomposed into a sparse fp16 outlier residual and a dense sub-byte index tensor into a per-group learned codebook. Two storage modes share one auto-select frontend and one fused decode kernel: V2 (per-channel Lloyd) and V2a (shared library of L=32 codebooks per layer). On Qwen3.5-122B-A10B under V2, XFP reaches 138 tok/s single-stream decode on workstation hardware (RTX PRO 6000 Blackwell, TP=2) at 94.49% GSM8K strict-match (3 seeds, n=3957), and is 49% faster than Marlin INT4 at TP=1. For models that do not fit in the target memory envelope, we present the H-Process: a quality-driven iteration over the two cosine thresholds that finds the operating point at which the model just fits while still producing sensible output. Three constraints define its search space: the operator-set thresholds, an OOM boundary at quantize-on-load, and a garbage boundary in generation (cosine similarity steers; benches verify). On Qwen3.5-397B-A17B (512 routed experts/layer), the H-Process fits the full expert population into 2x96 GB at ~3.4 effective bits and delivers 100.9 tok/s long-output decode at 66.72% GSM8K strict-match on the full 1319-problem set (single seed at submission; multi-seed evaluation in progress), exceeding INT4 with routed-expert pruning on memory, throughput, and accuracy simultaneously.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14844
PDF
-
Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization
2026-05-14 07:55:43Bin Huang, Xin Wang, Junwei Pan, Yongqi Zhou, Yifeng Zhou, Zhixiang Feng, Shudong Huang, Haijie Gu, Wenwu ZhuAbstract
Generative Recommendation (GenRec) models reformulate recommendation as a sequence generation task, representing items as discrete Semantic IDs used symmetrically as both inputs and prediction targets. We identify a critical dual-stage information bottleneck in this design: (1) the Input Bottleneck, where lossy quantization degrades fine-grained semantics, while popularity bias skews the learned representations toward frequent items, and (2) the Output Bottleneck, where imprecise discrete targets limit supervision quality. To address these issues, we propose AsymRec, an asymmetric continuous-discrete framework that decouples input and output representations. Specifically, Multi-expert Semantic Projection (MSP) maps continuous embeddings into the Transformer's hidden space via expert-specialized projections, preserving semantic richness and improving generalization to infrequent items. Multi-faceted Hierarchical Quantization (MHQ) constructs high-capacity, structured discrete targets through multi-view and multi-level quantization with semantic regularization, preventing dimensional collapse while retaining fine-grained distinctions. Extensive experiments demonstrate that AsymRec consistently outperforms state-of-the-art generative recommenders by an average of 15.8 %. The code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14512
PDF
-
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
2026-05-14 04:35:57Zhengjia Zhong, Shuyan Ke, Zaizhou Lin, Jiaqi Song, Hongyi Lan, Hui LiAbstract
Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks that limit expressiveness under heterogeneous data geometry. While recent dynamic quantizers like QINCo adapt codebooks to individual inputs and improve expressiveness, their strict sequential dependencies create decoding bottlenecks. We propose Residual Quantization via Mixture of Experts (RQ-MoE), a framework combining a two-level MoE with dual-stream quantization to enable input-dependent codebook adaptation for efficient vector quantization. RQ-MoE enables dynamic codebook construction and decouples instruction from quantization, facilitating parallel decoding. Theoretically, we show that standard Residual Quantization and QINCo can be recovered as constrained special cases of RQ-MoE, and derive a guideline for setting expert dimensionality in RQ-MoE. Extensive experiments show that RQ-MoE achieves state-of-the-art or on-par performance in reconstruction and retrieval, while providing 6x-14x faster decoding than prior vector quantization methods. The implementation is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14359
PDF
-
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
2026-05-14 03:57:25Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Jiayi Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong ChenAbstract
Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attribute this gap to standard discrete-tokenizer objectives being weakly aligned with text legibility and facial fidelity, as these objectives typically optimize generic reconstruction while compressing diverse content uniformly. To address this, we propose InsightTok, a simple yet effective discrete visual tokenization framework that enhances text and face fidelity through localized, content-aware perceptual losses. With a compact 16k codebook and a 16x downsampling rate, InsightTok significantly outperforms prior tokenizers in text and face reconstruction without compromising general reconstruction quality. These gains consistently transfer to autoregressive image generation in InsightAR, producing images with clearer text and more faithful facial details. Overall, our results highlight the potential of specialized supervision in tokenizer training for advancing discrete image generation.
Abstract (translated)
URL
https://arxiv.org/abs/2605.14333
PDF
-
High-Rate Quantized Matrix Multiplication II
2026-05-13 16:47:25Or Ordentlich, Yury PolyanskiyAbstract
This is the second part of the work investigating quantized matrix multiplication (MatMul). In part I we considered the case of calibration-free quantization, whereas here we discuss the setting where covariance matrix $\Sigma_X$ of the columns of the second factor is available. This setting arises in the ubiquitous task of weight-only post-training quantization of LLMs. Weight-only quantization is related to the problem of weighted mean squared error (WMSE) source coding, whose classical (reverse) waterfilling solution dictates how one should distribute rate between coordinates of the vector. We show how waterfilling can be used to improve practical LLM quantization algorithms (GPTQ), which at present allocate rate equally. A recent scheme (known as ``WaterSIC'') that only uses scalar INT quantizers is analyzed and its high-rate performance is shown to be (a) basis free (i.e., characterized by the determinant of $\Sigma_X$ and, thus, unlike existing schemes, is immune to applying random rotations); and (b) within a multiplicative factor of $\frac{2\pi e}{12}$ (or 0.25 bit/entry) of the information-theoretic distortion limit. GPTQ's performance, in turn, is affected by the choice of basis, but for a random rotation and actual $\Sigma_X$ from Llama-3-8B we find it to be within 0.1 bit (depending on the layer type) of WaterSIC, suggesting that GPTQ with random rotation is also near optimal, at least in the high-rate regime.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13768
PDF
-
High-Rate Quantized Matrix Multiplication I
2026-05-13 16:41:48Or Ordentlich, Yury PolyanskiyAbstract
This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of large language models (LLMs). We consider a Generic MatMul setting, where both matrices must be quantized (weight+activation quantization) without specific apriori (calibration) statistical information about the factors. We review the fundamental information-theoretic tradeoff between quantization rate and distortion (high-rate theory), and contrast those with the performance of popular quantization schemes (absmax INT and floating-point (FP)), for which we also derive accurate heuristic approximations. Part II of this paper studies the weight-only quantization setup where second-order statistics of the activation matrices are available at the encoder.
Abstract (translated)
URL
https://arxiv.org/abs/2601.17187
PDF
-
Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
2026-05-13 13:47:11Anuj Sadani, Deepak KumarAbstract
Personally Identifiable Information (PII) redaction usually replaces detected entities with placeholder tokens such as [PERSON], destroying the downstream utility of the redacted text for retrieval and Named Entity Recognition (NER) training. We propose a fully on-device pipeline that substitutes PII with consistent, type-preserving fake values: a 1.5 B mixture-of-experts token classifier (openai/privacy-filter) detects spans, a 1-bit Bonsai-1.7B Small Language Model (SLM) proposes contextual surrogates for names, addresses, and dates, and a rule-based generator (faker) handles patterned fields. We report a prompting finding more important than the quantization choice: with naive fixed three-shot demonstrations, the 1-bit SLM regurgitates demonstration outputs verbatim regardless of input; 1.58-bit Ternary-Bonsai-1.7B reproduces byte-identical failures, ruling out quantization as the cause. We fix this with locale-conditioned rotating few-shot demonstrations: a character-range heuristic picks a locale-pure pool and a per-input MD5 hash samples three demonstrations. With the fix, 482/482 unique Bonsai-1.7B calls succeed (no echoes) and produce locale-correct surrogates, although the SLM still copies from a small same-locale demonstration pool - a residual narrowness we quantify. On a 2000-document multilingual corpus, hybrid perplexity (PPL) beats faker in all six locales under a multilingual evaluator (XGLM-564M); length preservation is best-of-three in 4 of 6 locales. On downstream NER (400 train / 100 test, English), redact yields F1=0.000, faker 0.656, original 0.960; on a matched 160/40 subset including hybrid, faker (0.506) outperforms hybrid (0.346) at p < 0.001. We report this as an honest negative finding: SLM surrogates produce more natural text but a less varied training distribution, and downstream NER benefits more from variety than from naturalness.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13538
PDF
-
ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin
2026-05-13 13:35:16Jaeyung Kim, YoungJoon YooAbstract
Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However, VQ-VAE models must tokenize entire images using a finite set of codebook vectors, and this capacity limitation restricts their ability to capture rich and diverse representations. In this paper, we propose ArcCosine Additive Margin VQ-VAE (ArcVQ-VAE), a novel vector quantization framework that introduces a spherical angular-margin prior (SAMP) for the codebook of a conventional VQ-VAE. The proposed SAMP consists of Ball-Bounded Norm Regularization, which constrains all codebook vectors within a time-dependent Euclidean ball, and ArcCosine Additive Margin Loss, which encourages greater angular separability among latent vectors. This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization. Experimental results on standard image reconstruction and generation tasks show that ArcVQ-VAE achieves competitive performance against baseline models in terms of reconstruction accuracy, representation diversity, and sample quality. The code is available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.13517
PDF
-
RotVLA: Rotational Latent Action for Vision-Language-Action Model
2026-05-13 11:58:02Qiwei Li, Xicheng Gong, Xinghang Li, Peiyan Li, Quanyun Zhou, Hangjun Ye, Jiahuan Zhou, Yadong MuAbstract
Latent Action Models (LAMs) have emerged as an effective paradigm for handling heterogeneous datasets during Vision-Language-Action (VLA) model pretraining, offering a unified action space across embodiments. However, existing LAMs often rely on discrete quantization encode and decode pipelines, which can lead to trivial frame reconstruction behavior, limited representational capacity, and a lack of physically meaningful structure. We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation. Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics. A triplet frame learning framework further enforces meaningful temporal dynamics while avoiding degeneration. RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos with latent-action supervision. For downstream robot control, the flow-matching head is extended into a unified action expert that jointly denoises latent and robot actions. Here, latent actions serve as a latent planner, providing high-level guidance that conditions action generation. With only 1.7B parameters and 1700+ hours of pretraining data, RotVLA achieves 98.2% on LIBERO and 89.6% / 88.5% on RoboTwin2.0 under clean and randomized settings, respectively. It also demonstrates strong real-world performance on manipulation tasks, consistently outperforming existing VLA models.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13403
PDF
-
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
2026-05-13 09:49:56Lingchao Zheng, Yuwei Fan, Jun Li, Chengqiu Hu, Qichen Liao, Junyi Fan, Rui Shi, Fangzheng MiaoAbstract
Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators. On architectures with decoupled compute units (e.g., Ascend NPUs), dequantization operations can consume more cycles than the matrix multiplication itself, leaving the high-throughput tensor cores underutilized. This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM critical path. Instead of lifting low-bit weights to BF16 precision, MSD decomposes high-precision BF16 activations into multiple low-precision components, each of which can be multiplied directly with quantized weights via native hardware-accelerated GEMM. This approach shifts the computational paradigm from precision conversion to multi-scale approximation, avoiding INT8-to-BF16 weight conversion before GEMM. We instantiate MSD for two weight formats and derive tight error bounds for each. For INT8 weights (W4A16), two-pass INT8 decomposition achieves near 16 effective bits. For MXFP4 weights (W4A16), two-pass MXFP4 decomposition yields near 6.6 effective bits with error bound 1/64 per block surpassing single-pass MXFP8(5.24 bits) while maintaining the same effective GEMM compute time. We further derive closed-form latency and HBM traffic models showing that MSD avoids the Vector-Cube pipeline stall caused by dequantization and reduces KV cache HBM traffic by up to 2.5 times in attention. Numerical simulations on matrix multiplication and Flash Attention kernels confirm that MSD does not degrade accuracy compared to dequantization baselines, and in many settings achieves lower L2 error.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13915
PDF
-
Compact Latent Manifold Translation: A Parameter-Efficient Foundation Model for Cross-Modal and Cross-Frequency Physiological Signal Synthesis
2026-05-13 09:31:36Bo Cui, Xiaowen Song, Yaowen Zhang, Shunzhe Zhang, B. J. F. van Beijnum, Monique Tabak, Ying WangAbstract
The analysis of physiological time series, such as electrocardiograms (ECG) and photoplethysmograms (PPG), is persistently hindered by modality and frequency gaps stemming from heterogeneous recording devices. Existing foundation models typically rely on continuous latent spaces, which frequently suffer from severe modality entanglement, lack high-fidelity cross-frequency generative capacity, and impose high computational costs that prohibit edge-device deployment. In this paper, we propose Compact Latent Manifold Translation (CLMT), a highly parameter-efficient (0.09B) unified framework that bridges these gaps through a novel two-stage discrete translation paradigm. First, we introduce a Universal Tokenizer utilizing Hierarchical Residual Vector Quantization (RVQ) to decouple heterogeneous signals into isolated, well-structured discrete latent manifolds, effectively preventing inter-modality interference. Second, a Context-Prompted Latent Translator maps these discrete tokens across modalities by integrating static physiological priors, reframing complex signal synthesis as a pure latent sequence translation task. Extensive evaluations demonstrate that our 0.09B model significantly outperforms massive baselines. In cross-modal PPG-to-ECG synthesis, it resolves temporal phase drift and dramatically improves the clinical R-peak detection F1-score from 0.37 (baseline) to 0.83. Furthermore, in extreme cross-frequency super-resolution (25Hz to 100Hz), it successfully recovers high-frequency diagnostic landmarks, achieving an unprecedented Pearson correlation of 0.9956. By learning a universal discrete language for biological signals with a fraction of the computational footprint, our approach sets a new trajectory for edge-deployable, multi-modal medical foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2605.13248
PDF
-
Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations
2026-05-12 14:03:30Souptik Sen, Raneen Younis, Zahra AhmadiAbstract
Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizability with modality-specific structure. Continuous (implicit) methods preserve fine-grained priors but render generalization challenging, while discrete (explicit) approaches enforce shared prototypes at the expense of modality specificity. We introduce CoDAAR (Cross-modal Discrete Alignment And Reconstruction), a novel framework that resolves this long-standing trade-off by establishing semantic consensus across modality-specific codebooks through index-level alignment. This design uniquely allows CoDAAR to preserve modality-unique structures while achieving generalizable cross-modal representations within a unified discrete space. CoDAAR combines two complementary mechanisms: Discrete Temporal Alignment (DTA), which enables fine-grained temporal quantization, and Cascading Semantic Alignment (CSA), which promotes progressive cross-modal semantic agreement. Together, they establish a competition-free unified representation space. Trained with self-supervised reconstruction objectives on paired multimodal sequences, CoDAAR demonstrates robust cross-modal and cross-domain generalization. Across Cross-Modal Generalization benchmarks, including event classification, localization, video segmentation, and cross-dataset transfer, CoDAAR achieves state-of-the-art performance, establishing a new paradigm for discrete and generalizable multimodal representation learning.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12145
PDF
-
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
2026-05-12 07:58:58Inwoo Hwang, Hojun Jang, Bing Zhou, Jian Wang, Young Min Kim, Chuan GuoAbstract
We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion generation as a coarse-to-fine process. We quantize 3D motions into compositional discrete tokens across multiple skeletal-emporal scales of increasing granularity, learning to generate motion by autoregressively predicting next-scale token maps. To maintain structural integrity, our motion tokenizers and quantizers are explicitly designed so that discrete tokens at every scale strictly preserve the skeletal hierarchy. Additionally, we employ bitwise quantization and prediction, which efficiently scale up the tokenizer vocabulary to preserve motion details and stabilize optimization. Extensive experiments demonstrate that ScaleMoGen achieves state-of-the-art performance, establishing an FID of 0.030 (vs. 0.045 for MoMask) on HumanML3D and a CLIP Score of 0.693 (vs. 0.685 for MoMask++) on the SnapMoGen dataset. Furthermore, we demonstrate that our skeletal-temporal multi-scale representation naturally facilitates training-free, text-guided motion editing.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11704
PDF
-
PRISM: A Geometric Risk Bound that Decomposes Drift into Scale, Shape, and Head
2026-05-12 06:40:34Chieh-Yen Lin, Shao-Hua SunAbstract
Comparing post-training LLM variants, such as quantized, LoRA-adapted, and distilled models, requires a diagnostic that identifies how a variant has drifted, not only whether it has degraded. Existing similarity scores such as CKA and SVCCA can flag degradation, but they do not directly link representation drift to risk or mechanism. We propose PRISM, Proxy Risk Inference via Structural Mapping, which exploits the linear output head of LLMs and the empirically near-isometric structure of their backbones to derive a closed-form upper bound on the cross-entropy risk gap between a target model and a post-training variant. The bound is calibrated for variant ranking and decomposes drift into three independently measurable axes: scale mismatch, shape mismatch, and head divergence. Each axis corresponds to a distinct failure mode, including shape distortion under low-bit quantization, scale separability under LoRA forgetting, and head divergence under GGUF k-quantization. As a result, the dominant axis suggests a remediation direction rather than merely raising a degradation flag. Because the shape term is differentiable, the same geometry can also serve as a training-time regularizer against catastrophic forgetting. Across two model families and five benchmarks, PRISM ranks variants with mean Spearman correlations of 0.820 for post-training quantization and 0.831 for LoRA forgetting, and its axis-guided shape regularizer outperforms experience replay in aggregate at mitigating downstream forgetting.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11608
PDF
-
Efficient LLM-based Advertising via Model Compression and Parallel Verification
2026-05-12 06:04:38Wenxin Dong, Chang Gao, Guanghui Yu, Xuewu Jiao, Mingqing Hu, Qiang Fu, Peng Xu, Penghui Wei, Hui Xu, Yue Xing, Shuanglong Li, Lin LiuAbstract
Large language models (LLMs) have shown remarkable potential in advertising scenarios such as ad creative generation and targeted advertising. However, deploying LLMs in real-time advertising systems poses significant challenges due to their high inference latency and computational cost. In this paper, we propose an Efficient Generative Targeting framework that integrates adaptive group quantization, layer-adaptive hierarchical sparsification, and prefix-tree parallel verification to accelerate LLM inference while preserving generation quality. Extensive experiments on two real-world advertising scenarios demonstrate that our framework achieves significant speedup with acceptable quality degradation, making it operationally viable for practical deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2605.11582
PDF
