arXiv subjects

Jiawei Shao

Publications and source records attributed to Jiawei Shao.

At least 19 recordsLinked to original sources

arXiv2026

ProQuant: Progressive Quantization-aware Training for Edge MLLMs

Multi-modal large language models (MLLMs) with impressive perception and understanding capabilities will enable a range of downstream applications. However, their substantial computational and memory requirements hinder the real-world implementation, particularly for resource-constrained edge devices. Quantization has emerged as an effective solution for deploying large models. While post-training quantization (PTQ) successfully retains the performance at moderate bit-width (e.g., W8A8), it suffers from severe performance degradation under low-bit quantization (e.g., W4A8), especially for small-scale models that are more suitable for edge deployment. In this paper, we propose ProQuant, a novel weight-activation quantization-aware training (QAT) framework tailored for low-bit MLLMs. First, to align the limited finetuning dataset distribution with the pretrained dataset distribution, we propose a self-relabeling (SRL) scheme to resample the responses of the open-source multimodal dataset. Second, we are the first to take a decoupled view of multi-modal (MM) understanding and language modeling abilities. We propose a progressive block activation (PBA) mechanism to prioritize the MM understanding recovery. We also introduce a vision-sensitive factor $\vecτ$ that effectively identifies the MM-critical layers. Extensive experiments across various benchmarks, covering models with 2B-8B parameters, show that ProQuant significantly outperforms existing methods. For example, our W4A8 Qwen3-VL-2B-Instruct improves average accuracy by impressively 6.6% and achieves performance comparable to full precision counterparts with only approximately 1% performance drop. Code is available at https://github.com/yufeixue-ai/ProQuant/.

cs.CV↗

arXiv2026

Intrinsic Raman Modes and Crystal Symmetry of Altermagnetic $α$-MnTe

Crystal symmetry governs the physical properties of materials and provides the framework for interpreting their microscopic excitations and macroscopic responses. In altermagnets, the crystal symmetries that relate opposite-spin sublattices give rise to momentum-dependent spin splitting despite compensated magnetization. Determining the real crystal symmetry is therefore essential for understanding the intrinsic electronic and magnetic properties. For the altermagnetic semiconductor $α$-MnTe, conflicting Raman assignments have left both its intrinsic lattice excitations and its crystal symmetry unresolved. Here we combine high-resolution Raman and second-harmonic generation (SHG) spectroscopy with first-principles calculations to distinguish intrinsic lattice excitations from Te-derived spectral contributions and to examine bulk inversion symmetry of $α$-MnTe. We show that several prominent Raman features previously assigned to $α$-MnTe instead originate from segregated Te clusters or precipitates. The remaining intrinsic Raman response consists of a single Raman-active mode assigned to the calculated $E_{2g}$ phonon, consistent with the centrosymmetric $D_{6h}$ symmetry. The SHG response agrees with surface electric-dipole and bulk electric-quadrupole contributions expected for a centrosymmetric $D_{6h}$ crystal, supporting the preservation of bulk inversion symmetry in $α$-MnTe. Our findings revise the Raman assignments in $α$-MnTe and provide a basis for interpreting its altermagnetic properties within the appropriate crystal-symmetry framework.

cond-mat.mtrl-sci↗

arXiv2026

Visual Cache Reuse for Efficient Multimodal Inference

Vision-language model (VLM) inference incurs substantial prefill latency and memory overhead due to the long visual token sequences of large visual inputs. Existing serving systems typically exploit exact cache reuse through prefix caching or position-independent caching, overlooking the potential of approximate caching in real-world workloads. However, directly reusing an approximate cache entry may introduce spurious visual information, which naive approaches that select a subset of important visual tokens for recomputation fail to adequately mitigate this risk. We present VisMemo, an efficient serving system that enables approximate KV cache reuse for modern VLMs. Its core is a system-algorithm co-design that combines an entropy-aware KV cache reuse algorithm with differentiated cache management. Specifically, VisMemo uses patch entropy to identify reuse candidates and warmup attention to prioritize recomputation based on the current query. To support the large cache capacity across GPU memory, CPU memory, and SSD storage, VisMemo applies distinct I/O and cache policies to exact and approximate hits: sparse patch-level I/O for approximate hits, prioritized retention for exact hits, and a reserved CPU victim cache for preset entries selected using offline workload priors and online reuse observations. VisMemo further optimizes the memory access path between the inference engine and the storage backend, eliminating redundant caching and unnecessary data movement. Experiments on multiple public datasets show that VisMemo preserves output quality under approximate reuse. On a real-world production trace, VisMemo increases the overall cache hit rate from 27.78% to 61.45% and reduces prefill latency by up to 48.3% at 8K input tokens.

cs.OS↗

arXiv2026

Luttinger Liquid Behavior in a Single-Layer Nickelate La1.4Sr0.6NiO4

The discovery of high-temperature superconductivity in bilayer and trilayer nickelates has spurred intense interest in the Ruddlesden-Popper nickelates; yet the fundamental properties of the NiO2 layer remain obscured by interlayer coupling. It is therefore imperative to investigate the electronic properties of their single-layer counterpart to isolate the intrinsic physics of the NiO layer. In this work, we present a systematic study of the single-layer nickelate La1.4Sr0.6NiO4 using high-resolution angle-resolved photoemission spectroscopy (ARPES) and theoretical calculations. We reveal strong electron correlation effects, manifested by high-energy kinks in band dispersions and a pronounced orbital-dependent band renormalization. Interestingly, we observe a quasi-one-dimensional electronic structure characterized by straight Fermi surface sheets along the diagonal momentum directions. Such square Fermi surface topology facilitates non-Fermi liquid behavior consistent with the Luttinger liquid model, as evidenced by the power-law spectral function, robust temperature scaling, and the observation of spin-charge separation. Our results therefore not only unveil an exotic Luttinger liquid behavior emerging from the unexpected dimensional reduction in an intrinsically quasi-two-dimensional nickelate but also provide a new perspective for understanding the intriguing physics in multilayer nickelates.

cond-mat.supr-con↗

arXiv2026

ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications

Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-demand construction process: information-rich charts make chart question answering (Chart QA) suitable for probing coupled perception and reasoning. Automated Chart QA construction is intended to shorten the benchmark-development cycle by turning identified gaps into targeted samples on demand. Current methods, however, commonly separate target guidance from scratch generation: target-guided systems often require prepared data, charts, or templates, while scratch-generation systems primarily ensure artifact validity, without explicitly controlling whether newly synthesized requirements and content remain aligned with an externally specified diagnostic target. We introduce ChartBmkAgent, which turns an identified capability gap into targeted diagnostic evidence by constructing complete Chart QA samples from sparse error-taxonomy specifications. Throughout construction, a central harness governs specialized agents, requires stage-specific evidence of alignment with the original error category, and records the basis for each acceptance decision. On 300 taxonomy-wide samples, MLLM accuracies ranged from 32.7% to 84.3% with distinct category profiles, showing that generated samples reveal capability differences. Across three source-model comparisons, targeted follow-ups scored 50.0% versus 82.2% on matched controls ($p=8.96\times10^{-6}$); all six cross-model comparisons had the same direction, demonstrating targeted validation and diagnostic-data generation. Multiple evaluator models assessed whether each sample tested its specified error category; 86.4% met this criterion, providing empirical evidence of target preservation.

cs.AI↗

arXiv2026

Task-Oriented Visual Feature Compression via Residual Vector Quantization for Device-Edge Multimodal Inference

Large multimodal models (LMMs) support diverse visual understanding and reasoning tasks but are often impractical to run entirely on resource-constrained devices. Device-edge co-inference reduces device computation, yet transmitting visual data over bandwidth-limited uplinks can introduce substantial delay. Task-oriented feature compression (TOFC) reduces the payload through feature aggregation and entropy coding. However, continuous-feature coding remains costly, and query-agnostic aggregation may discard task-relevant local evidence. We propose query-guided task-oriented feature compression (Q-TOFC) for device-edge multimodal inference. Q-TOFC employs residual vector quantization (RVQ) to encode each merged feature as a compact sequence of codebook indices, reducing its representation cost and allowing more features to be transmitted. It further incorporates query relevance into feature aggregation and uses a quantization error compensation adapter to mitigate the distortion introduced by discrete quantization. Experiments on seven multimodal benchmarks show that Q-TOFC reduces the visual payload by 53.6% relative to TOFC while maintaining comparable average normalized task performance. End-to-end latency evaluations further demonstrate lower latency under bandwidth-constrained uplinks.

cs.CV↗

arXiv2026

Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs

Hybrid LLMs interleave full-attention layers with linear-attention layers to reduce long-context inference cost, but this structure complicates prefix caching. Full-attention KV caches are token-addressable, whereas linear-attention layers maintain recurrent states that cannot be rolled back to arbitrary prefix boundaries. Existing systems materialize recurrent-state checkpoints, restricting prefix reuse to checkpoint-aligned positions. We present SuffixReplay, the first prefix caching system that lets hybrid LLMs reuse cached prefixes at every cache-supported page boundary without materializing recurrent-state checkpoints. Our key insight is to just let linear states forget the distant past. Modern linear-attention mechanisms use recurrent decay and gating to attenuate the influence of old inputs. Therefore, instead of checkpointing every prefix boundary, SuffixReplay approximates the state at a matched boundary by replaying only a recent suffix of the layer's input hidden states, which we retain as anchors. At the algorithmic level, SuffixReplay combines layer-wise and token-wise anchor sparsity with a bounded replay budget to control storage, computation, and quality. At the system level, it uses an independently managed anchor sidecar and a pipelined replay path to overlap anchor movement and state reconstruction with the native serving pipeline. We evaluate SuffixReplay on three hybrid LLMs: OLMo-Hybrid-7B, Qwen3.5-4B, and Qwen3.6-27B-FP8. Across these models, SuffixReplay retains 91.4-100% of full-prefill quality on average across LongBench and RULER, while using only 0.36-0.51x the amortized per-token storage of SGLang's default 8192-token checkpoint cache. Integrated into SGLang, SuffixReplay reduces median TTFT by 15-70% on branching workloads, sustains 2.3-4.3x SGLang's throughput when the working set exceeds HBM, and matches SGLang on high-hit continuation traffic.

cs.AI↗

arXiv2026

RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse

Cross-request KV caching reduces the prefill cost of Retrieval-Augmented Generation (RAG), but conventional prefix caching severely limits cache reuse across requests. Position-Independent Caching (PIC) removes this constraint by reusing independent chunks, but their KV states miss cross-chunk interactions. Existing methods selectively recompute token states to recover these missing interactions, but primarily allocate the recomputation budget to selecting which states to recompute, while fixing the recomputation context to the full causal prefix. We introduce RelaxKV, which formulates selective cache repair as a joint allocation problem over repair targets and recomputation context. Guided by the user query, RelaxKV identifies layer-specific repair targets and restricts their recomputation to a query-relevant context, reducing attention computation. Across four decoder models, RelaxKV at a 15% anchor ratio improves aggregate LongBench performance over ProphetKV on all models. On Qwen3-14B, RelaxKV provides a stronger quality-TTFT trade-off than ProphetKV across a 5%-30% anchor-ratio sweep, and achieves the best selective results on RULER-MV and LV-Eval at 16K and 32K context lengths. Controlled ablations further demonstrate the importance of recomputation context selection.

cs.AI↗

arXiv2026

Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality

Under the AI Flow framework, communication networks distribute intelligence across devices, edge servers, and clouds, and computation at the receiver becomes a resource that can substitute for transmitted bits. Generative video compression (GVC) embodies this exchange by sending compact tokens with ultra-low bitrate and letting a generative decoder synthesize the video, yet how much bandwidth savings a unit of decoder compute actually achieves has never been quantified. To fill this vacancy, we model reconstruction quality as a two-factor power law in data rate and decoder compute, which fits measured DISTS of two GVC decoders with a mean error below 3%, and define the information capacity (IC) as the negative logarithmic slope along an iso-quality contour, namely the fraction of rate saved per fractional increase in compute at identical quality. IC is dimensionless and unit-invariant, thus enabling an architecture-agnostic comparison. It forms a field over the operating plane, locating where additional denoising steps are worth their cost. Across five datasets, the 14B decoder trades more compute for fewer rate about ten times more efficiently than the 1.3B decoder. IC also varies significantly across datasets, indicating imbalanced performance on the rate-compute trade-off in GVC methods.

cs.CV↗

arXiv2026

SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models

Large language models (LLMs) have demonstrated remarkable capabilities across diverse language tasks, motivating their extension to vision-language models (VLMs) for multimodal understanding. However, billion-parameter VLMs incur substantial memory and computational costs that hinder deployment in resource-constrained settings. Post-training quantization (PTQ) compresses models and accelerates inference without retraining, yet remains underexplored for VLMs. We identify two intrinsic VLM activation properties in PTQ: (1) visual over-representation, where vision tokens are excessive and often redundant, and (2) the modality gap separating text and vision tokens in the latent feature space. Prior methods largely overlook these properties, leading to quantization performance degradation. To address this mismatch, we propose SalQ-VLM, an importance-aware PTQ framework that prioritizes salient tokens and suppresses redundant vision tokens during calibration. We derive a gradient-driven importance factor that captures token-level importance variance and is theoretically grounded in the relationship among loss perturbation, activation errors, and output gradients. SalQ-VLM obtains this factor through a single lightweight block-wise gradient-caching pass and incorporates it into the layer-wise reconstruction objective. Because SalQ-VLM modifies only calibration, it adds no inference-time operations and remains compatible with existing high-performance kernels. Extensive evaluations across benchmarks and backbones show that SalQ-VLM consistently outperforms strong PTQ baselines, especially under ultra-low-bit quantization. Notably, it improves MME-RealWorld accuracy by 16.45% under INT2g128 quantization.

cs.CV↗

arXiv2026

Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts

On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories. However, scaling OPD to long-horizon reasoning exposes a reliability and efficiency problem: standard OPD assigns every candidate the same long rollout budget, even though some trajectories may quickly become weakly aligned with the teacher and provide less useful supervision. Prior analyses suggest that teacher--student compatibility is important for OPD success, motivating early-prefix top-k overlap as a proxy for continuation value. Continuing low-overlap trajectories to the full rollout length may cause them to drift further from the teacher as generation proceeds, increasing computational cost while providing limited distillation benefit. To address this, we introduce Prefix-Guided On-Policy Distillation (PG-OPD), a rollout-allocation framework that estimates continuation value from fixed-length prefixes. PG-OPD computes teacher-student top-k overlap in an early probe window and allocates long rollouts only to high-overlap candidates, while stopping the rest at the prefix length. Across teacher--student combinations on AMC, AIME, and HMMT benchmarks, PG-OPD achieves up to a 4.80-point accuracy gain and up to a 2.46x wall-clock speedup across configurations. These results demonstrate that using early-prefix compatibility to guide candidate pruning can improve both training efficiency and reasoning performance.

cs.LG↗

arXiv2026

LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs

LLM serving is increasingly accelerated by position-independent caching (PIC). Existing PIC methods, however, are built for full-attention models, where a token-indexed KV cache underlies its core operations: matching reusable token chunks, concatenating their KV entries, and selectively recomputing a few tokens to restore cross-chunk context. Hybrid LLMs break these primitives---they replace most attention layers with linear recurrences that expose only a fixed-size state, leaving no token-indexed KV to concatenate or to locally repair. This raises a natural question: can PIC benefit hybrid models, and what would it take? We present LinearKV, a training-free hybrid-PIC framework. Its key insight is a \emph{decoupled initialization}: each linear layer maps its $K$ matched local states to a single initial state, while full-attention layers concatenate their KV as before. LinearKV is therefore compatible with existing PIC methods, reusing their token selection and recomputation as-is. Under this framework, we find that a \emph{single cached state} suffices as the linear layer's initializer. The algebraically principled alternative---composing all $K$ cached states into the exact full-prefix state, as concurrent work HYPIC does---is unnecessary and, on some architectures, even harmful. We compare the two across three hybrid models and three PIC selectors. On the two GDN models the two tie, both recovering most of full quality (up to $92\%$); on the Mamba-2 model, exact composition instead collapses under every selector---under EPIC, for instance, it recovers only $46.6\%$ of full quality, versus $86.8\%$ for a single cached block initializer. A single state initializer is also cheaper, cutting time-to-first-token to $0.46\times$ full prefill versus a further $5$--$17\%$ overhead for exact composition; results hold across LongBench QA and RULER at 8K--32K.

cs.AI↗

arXiv2026

BPPO: Binary Prefix Policy Optimization for Efficient GRPO-Style Reasoning RL with Concise Responses

Group Relative Policy Optimization (GRPO) is widely used for training reasoning models, but updating all sampled completions in each group incurs substantial cost and can reinforce verbose reasoning trajectories. In this paper, we study whether all completions provide equally useful update signals in GRPO-style reasoning RL. Our gradient-similarity analysis shows that, within the same prompt group, same-class completions often induce highly similar update directions, whereas correct-incorrect pairs provide more distinct contrastive signals. Motivated by this observation, we propose Binary Prefix Policy Optimization (BPPO), which uses the shortest correct completion and the shortest incorrect completion as a compact update unit while preserving full-group advantage normalization. BPPO further improves efficiency with adaptive completion scheduling and prefix-focused optimization; by updating only response prefixes, it avoids reinforcing redundant suffixes and encourages more concise responses. Experiments on GSM8K, MATH, and Geo3K show that BPPO achieves up to 6.08x speedup over GRPO while maintaining competitive accuracy, and reduces mean response length by approximately 30-50% without modifying the reward with an explicit length penalty.

cs.LG↗

arXiv2026

Task-Oriented Communication for Human Action Understanding via Edge-Cloud Co-Inference

The expanding application of smart sensing has created a growing demand for the accurate understanding of human action at the network edge. Traditional approaches require massive video data to be transmitted from resource-constrained edge devices to powerful cloud servers, incurring prohibitive uplink bandwidth consumption and unacceptable latency while raising privacy concerns. To overcome these bottlenecks, we propose a task-oriented communication framework for human action understanding (TOAU) through edge-cloud collaboration. Our framework utilizes a monocular pose estimator to extract continuous joint coordinates from raw videos, followed by a vector quantized variational autoencoder (VQ-VAE) to convert these coordinates into discrete motion tokens. Consequently, only a compact sequence of codebook indices is transmitted over the network, consuming as few as 9 bits per frame and avoiding privacy leakages. At the cloud server, a lightweight projector aligns these motion tokens with the embedding space of a large vision-language model (VLM) to facilitate complex action understanding, which is trained with an efficient instruction tuning paradigm. Comprehensive evaluations on three benchmarks demonstrate that our TOAU system reduces the transmission payload to approximately 1\% and the system latency to around 20\% compared to video codec-based solutions, while delivering comparable action understanding accuracy.

eess.SP↗

arXiv2026

Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks

Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Test-Oriented Education, and argue that it rests on a fragile assumption: that benchmark scores directly reflect genuine generalization. In practice, however, such scores may conflate exam-oriented competence with principled capability, especially when contamination and semantic leakage are difficult to exclude from modern training pipelines. We therefore propose an audit framework for analyzing contamination sensitivity and score confidence in LLM benchmarks. Using a router-worker setup, we compare a clean-control condition with noisy conditions in which benchmark problems are systematically deleted, rewritten, and perturbed before being passed downstream. For a genuinely clean benchmark, noisy conditions should not consistently outperform the clean-control baseline. Yet across multiple models, we find widespread but heterogeneous above-baseline gains under noisy conditions, indicating that benchmark-related cues may be reassembled and can reactivate contamination-related memory. These results suggest that similar benchmark scores may carry substantially different levels of confidence. Rather than rejecting benchmarks altogether, we argue that benchmark-based evaluation should be supplemented with explicit audits of contamination sensitivity and score confidence.

cs.AI↗

arXiv2026

Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise

Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic. However, both traditional standardized codecs and neural video compression (NVC) methods struggle to encode these videos efficiently due to inadequate usage of temporal redundancy and severe distribution gaps between training and test data, respectively. While recent generative compression methods improve perceptual quality, they introduce hallucinated details that are unacceptable in authenticity-critical applications. To overcome these limitations, we propose a positive-incentive camera (PIC) framework for static scene videos, where short-term temporal changes are reinterpreted as positive-incentive noise to facilitate NVC model finetuning. By disentangling transient variations from the persistent background, structured prior information is internalized in the compression model. During inference, the invariant component requires minimal signaling, thus reducing data transmission while maintaining pixel-level fidelity. Experiment results show that PIC achieves visually lossless reconstruction for static scenes at an extremely low compression rate of 0.009%, while the DCVC-FM baseline requires 20.5% higher Bjøntegaard delta (BD) rate. Our method provides an effective solution to trade computation for bandwidth, enabling robust video transmission under adverse network conditions and economic long-term retention of surveillance footage.

eess.IV↗

arXiv2026

Ruyi2.5 Technical Report

We present Ruyi2.5, a multimodal familial model built on the AI Flow framework. Extending Ruyi2's "Train Once, Deploy Many" paradigm to the multimodal domain, Ruyi2.5 constructs a shared-backbone architecture that co-trains models of varying scales within a single unified pipeline, ensuring semantic consistency across all deployment tiers. Built upon Ruyi2.5, Ruyi2.5-Camera model is developed as a privacy-preserving camera service system, which instantiates Ruyi2.5-Camera into a two-stage recognition pipeline: an edge model applies information-bottleneck-guided irreversible feature mapping to de-identify raw frames at the source, while a cloud model performs deep behavior reasoning. To accelerate reinforcement learning fine-tuning, we further propose Binary Prefix Policy Optimization (BPPO), which reduces sample redundancy via binary response selection and focuses gradient updates on response prefixes, achieving a 2 to 3 times training speedup over GRPO. Experiments show Ruyi2.5 matches Qwen3-VL on the general multimodal benchmarks, while Ruyi2.5-Camera substantially outperforms Qwen3-VL on privacy-constrained surveillance tasks.

cs.CL↗

arXiv2026

Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives

Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic forgetting under real-world scenario shifts, we construct a multimodal visual understanding dataset (MSVQA), covering four distinct scenarios and perspectives: high-altitude, underwater, low-altitude, and indoor environments. Furthermore, we propose UNIFIER (mUltimodal coNtInual learning with MLLMs From multi-scenarIo pERspectives), a continual learning (CL) framework designed to address visual discrepancies while learning different scenarios. Compared to existing CL methods, UNIFIER enables knowledge accumulation within the same scenario and mutual enhancement across different scenarios via Vision Representation Expansion (VRE) and Vision Consistency Constraint (VCC). Experimental results show that UNIFIER improves the last-step VQA scores by 2.70%~10.62% and the last-step F1 scores by 3.40%~7.69% compared to the state-of-the-art method, QUAD, in 20-step cross-scenario continual learning tasks. MSVQA dataset is available at https://huggingface.co/datasets/Kaij00/MSVQA.

cs.CV↗