跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 13:05 — 2026-11-08 13:05（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 18 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
新论文 · v1arXiv:2611.04673

Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning

Yao Wang, Zehua Ma, Weiming Zhang, Han Fang

原文摘要

Indirect Prompt Injection (IPI) poses a critical threat to LLM agents. Existing defenses largely focus on whether an injection induces a new tool invocation or unintended action. In this paper, we study a different attack surface, parameter poisoning, where the attacker preserves the intended action but manipulates one or more tool arguments, such as a recipient or other task-critical value. Such attacks are difficult to detect because no new action is introduced, while parameter changes themselves are often legitimate parts of the user's request. Our key insight is that the legitimacy of a parameter change should be determined by the trust of the information flow that produces it under the user query. The query induces a task-specific trust hierarchy over available information fields: some are trusted to determine particular parameters, while others should have little or no influence. Based on this insight, we propose AuthorityFlow, a three-stage parameter-level defense. First, it interprets the user query to construct a task-specific trust hierarchy over the information fields available to the agent. Second, for each tool argument, it traces the information flow that produces its current value and attributes the value to its supporting field. Finally, it accepts the value only when that field is trusted to determine the parameter under the current task, allowing high-trust changes while flagging low-trust influence as potential parameter poisoning. We further introduce FactAuthBench for evaluating parameter poisoning in LLM agents. Without defense, the attack success rate reaches 93.06%. AuthorityFlow reduces it to 9.03%, while retaining 82.64% benign task utility compared with 90.28% without defense. Our results show that effective IPI defense requires reasoning not only about what action an agent takes, but also about which information is trusted to determine its parameters.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04289

When Debate Amplifies Risk: Social-Bias Vulnerabilities in Multi-Agent Safety Deliberation

Qinghua Mao, Xi Lin, Yuxin Qi, Zihao Xu, Jinze Gu, Yuliang Chen

原文摘要

Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, social biases such as conformity pressure and authority deference can override evidence-grounded safety boundaries. In this work, we investigate whether the social structure of deliberation can paradoxically amplify latent Web safety risks. We introduce SafeConflict-Bias, a controlled counterfactual diagnostic protocol spanning six core Web risk categories, which holds queries and retrieved evidence strictly invariant while isolating conversational majority sway, authority cues, and confidence asymmetry. Empirical evaluation across diverse proprietary and open-source backbones reveals that while isolated models reliably reject unsafe guidance, standard MAD catastrophically capitulates to social pressure---surging unsafe adoption from 0.0\% up to 100.0\% and systematically silencing safe minority evidence. To resolve this systemic fragility without retraining or debate regeneration, we propose RiskTrace-Debias, an inference-time auditing framework uniting evidence-first precommitment, social-metadata masking, and consistency-gated arbitration. RiskTrace-Debias suppresses worst-case unsafe adoption to $\le 2.0\%$ across all architectures without inducing over-refusal, while generating verifiable provenance traces to audit interpersonal manipulation in Web deliberation.

cs.CR · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02310

Detect, Repair and Audit: A Hierarchical Multi-Agent Defense Against Adversarial Attacks in Energy Forecasting

Zewei Shi, Ruoxi Sun, Minhui Xue, Feng Liu, Hua Ma, Xingliang Yuan, Surya Nepal

原文摘要

Accurate electricity-demand forecasting is essential for the modern energy infrastructure. Recently, Times-Series Large Language Models (TS-LLMs) have emerged as a promising approach to forecasting more accurate demand from historical consumption data in zero- and few-shot settings, helping energy operators effectively plan supply and allocate energy resources. However, these models are vulnerable to compromised sensor inputs that can distort forecasts and lead to erroneous market orders or unnecessary load shedding. Existing defenses focus primarily on end-device forecasting, overlooking the distinct data-drift, latency, and audit requirements across energy infrastructure. To address this gap, we extract from major energy standards and regulatory frameworks a three-layer conceptual model that captures the security postures for each layer. Guided by this model, we develop a Multi-Agent Reinforcement Learning (MARL) detector coupled with signal repair at local control centers, designed to mitigate distributional data drift through complementary feature-based detection and clean-reference-calibrated repair while meeting latency budgets. We further deploy an evidence-grounded LLM auditing agent with human-in-the-loop validation for audit-critical Virtual Power Plants (VPPs). In our evaluation, the best MARL configuration achieves an F1 score above 0.91 across all dataset-attack pairs, while signal repair reduces adversarial-to-clean input Relative Squared Error (RSE) by up to 83%. The few-shot auditor detects 77.78% of attacks in the Sherlock dataset. On the evaluated hardware, detection and repair require 7.95 ms on average, with a worst-observed latency of 14.50 ms, remaining within the local-center latency budget informed by IEEE 1646.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01581

Recursive Self-Improvement of Exoskeleton Assistance Policies through Human-in-the-Loop Feedback

Muyuan Ma, Shuo Jiang, Lijun Han, Xinpan Meng, Zhenghua Ma, Xiuze Xia, Houcheng Li, Long Cheng

原文摘要

To reduce reliance on manual design and extensive parameter tuning, a framework for the autonomous evolution of exoskeleton assistance policies through human feedback is proposed. Assistance policies are autonomously generated as executable control code by an intelligent agent and evaluated in experiments with human participants. Subjective user feedback, movement performance, and muscle activation measurements are incorporated into policy assessment. Based on these assessments, policy deficiencies are autonomously identified and the control code is revised by the agent for subsequent trials. A closed loop of policy generation, human feedback, evaluation, and autonomous refinement is thereby established. The framework is evaluated using GPT, DeepSeek, GLM, and Kimi, and initial assistance performance and refinement outcomes are compared across models. Despite differences in initial performance, effective assistance is achieved with all four models after a single autonomous refinement iteration under the tested conditions. Across three tasks, biceps and triceps muscle activation levels are reduced by 29.4% and 35.2%, respectively, compared with those measured without an exoskeleton. However, limited adaptability to unexpected situations is observed, indicating that further improvements in robustness and safety are required.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01578

Recoverability-Aware Evaluation of Diffusion Video Inpainting and Object Removal

Yanliang Qi, Jiacheng Ding, Cong Guo, Peihua Mai

原文摘要

Video inpainting for object removal is scored over the whole hole, although the background behind the object is visible in other frames of the shot for some hole pixels and in no frame for others. A whole-hole score therefore mixes copying with generation and cannot show which of the two a remover does well. To separate the two, we propose recoverability-stratified evaluation, in which a point tracker run on the clean video labels each hole pixel by whether and how far away it is observed, so that fidelity and temporal stability can be reported per stratum against a copy reference. To reuse the observed content, we also propose evidence-guided sampling (EGS), which blends tracked colors into the clean-latent prediction of a video diffusion remover without training. On DAVIS, the perceptual advantage of three diffusion removers over flow propagation shrinks where the content is visible a few frames away (LPIPS difference-in-differences +0.046 to +0.056 against E2FGVI-HQ), and real paired captures show the same pattern for two of them. Their DAVIS hole warping error is two to four times that of ProPainter, and copying along clean-video tracks lowers their recoverable LPIPS by a quarter to two fifths. EGS closes 43% and 56% of the gap to this copy reference on held-out DAVIS when its colors come from clean-video tracks. With colors tracked on the masked input, a pre-registered confirmation finds no gain on MiniMax-Remover and a loss on ROSE. Diffusion removers thus leave observed content unused on DAVIS, and training-free reuse does not yet hold with tracked evidence.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01573

Spend the Bits Where the Tiny Objects Are: Rate-Utility Region Coding for Aerial Detection

Yanliang Qi, Jiacheng Ding, Cong Guo, Peihua Mai

原文摘要

Bandwidth-limited aerial cameras must compress their images before a remote detector can find the many tiny objects in them. Threshold-based region-of-interest (ROI) coding sends only confidently detected regions, and because tiny objects provide limited visual evidence and often score low, it can discard the regions that contain them. We propose rate-utility region coding (RUO), which sends a region when its expected detection utility justifies its measured byte cost, choosing to drop it or to send it at low or high quality with one multiplier shared across images. RUO trains no model, uses a standard image codec and decodes in a few milliseconds. On all 1,610 VisDrone-DET test-dev images, RUO uses 42.4% fewer bits than a tuned threshold-based ROI coder, averaged over their shared tiny-object average precision (AP) range. RUO also needs fewer bits for tiny objects than the AV1 Image File Format (AVIF), High Efficiency Video Coding (HEVC) and three published learned codecs, and its advantage over threshold-based ROI coding persists when the sender and receiver use different detectors. For AP over all object sizes RUO needs 25.4% more bits than the tuned ROI coder, because its allocation drops large regions first at low rates, so it suits tasks that target tiny objects. We plan to release the code.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01534

AbacusGS: Gaussian Splatting without Per-Splat Sorting

Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai

原文摘要

3D Gaussian Splatting sorts every splat by depth in every frame. Viewers that draw splats with the hardware rasterizer and sort them on the CPU, as most web and mobile viewers do, spend most of the frame time in this sort. We present AbacusGS, which stores the blending order of a 3DGS scene in the scene layout. AbacusGS groups the splats into octree boxes of at most 128 splats and stores each box in order along an axis chosen at write time. In each frame, AbacusGS sorts only the visible boxes, and one dot product per box decides whether the box is read forward or backward. A short order-aware fine-tuning converts an existing 3DGS model, and the over operator of 3DGS stays unchanged. On 13 standard scenes, AbacusGS loses 0.13 dB PSNR on average against an equally fine-tuned 3DGS model. In an OpenGL viewer that orders splats on the CPU, AbacusGS renders frames 4.5 times faster than per-splat sorting. We also present a compact format of 17 bytes per splat and a CUDA tile renderer that use the same order. The code will be released.

cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01467

See, Think, Use: Diagnosing Perception and Reasoning Failures in VLMs

Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai

原文摘要

We present See, Think, Use, a protocol that traces each answer of a vision-language model to perception, reasoning or the use of perception. The diagnosis shows a developer which stage to improve and directs test-time compute to the stage that fails. Benchmarks score the final answer, and an answer that rests on the image earns the same credit as a guess or a memorized prior. The protocol asks the model two extra questions per item and needs no access to its weights. A localization probe asks for a box around every instance and measures seeing, and a text-replacement probe answers from a description and measures thinking. Use is the rate at which the answer follows the model's own perception across counterfactual image pairs. The rate needs no answer labels, because the question and its prior are the same on both images. On two model families and six datasets the protocol shows that the knob that helps follows the task family. Answers follow the model's perception except on images that contradict a common prior, and asking the model to localize first repairs this failure when its boxes are right. Allocating compute by the measured stages comes close to the best uniform policy at lower cost and beats a random allocation of the same compute wherever a knob raises the short stage. We will release the code, the prompts and the per-question outputs.

cs.CV · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.11176

Precision Synthesis of Multi-Tracer PET via VLM-Modulated Rectified Flow for Stratifying Mild Cognitive Impairment

Shuijin Lin, Shaozhen Yan, Tuo Liu, Haifeng Wang, Chunfeng Lian, Jie Lu, Jianhua Ma, Lin Xie

原文摘要

The biological definition of Alzheimer's disease (AD) relies on multi-modal neuroimaging, yet the clinical utility of positron emission tomography (PET) is limited by cost and radiation exposure, hindering early screening at preclinical or prodromal stages. While generative models offer a promising alternative by synthesizing PET from magnetic resonance imaging (MRI), achieving subject-specific precision remains a primary challenge. Here, we introduce DIReCT$++$, a Domain-Informed ReCTified flow model for synthesizing multi-tracer PET from MRI combined with fundamental clinical information. Our approach integrates a 3D rectified flow architecture to capture complex cross-modal and cross-tracer relationships with a domain-adapted vision-language model (BiomedCLIP) that provides text-guided, personalized generation using clinical scores and imaging knowledge. Extensive evaluations on multi-center datasets demonstrate that DIReCT$++$ not only produces synthetic PET images ($^{18}$F-AV-45 and $^{18}$F-FDG) of superior fidelity and generalizability but also accurately recapitulates disease-specific patterns. Crucially, combining these synthesized PET images with MRI enables precise personalized stratification of mild cognitive impairment (MCI), advancing a scalable, data-efficient tool for the early diagnosis and prognostic prediction of AD. The source code will be released on https://github.com/ladderlab-xjtu/DIReCT-PLUS.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.28591

Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

Haomin Qi, Xingliang Wang, Xuanqi Gao, Baihui Sang, Xin Zhang, Minghua Ma, Pengfei Gao, Yu Kang 等 12 位作者

原文摘要

Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests (PRs) into verified tasks on healthy modern revisions of the same repository. It aligns historical evidence with evolved code, reconstructs task states through Patch Reversal, Code Mapping, or Agent Reconstruction, and validates the lifecycle from a healthy base to a task state and a restored state. By deriving multiple tasks grounded in developer evidence from maintained environments, Change2Task provides executable data for coding agent training and evaluation while reducing repeated environment setup, storage, and task construction effort. We evaluate five coding agent task families: Bug Fix, Feature Addition, Test Generation, Application Programming Interface (API) Migration, and Security Repair. Starting from 1,130 source changes eligible for construction, Change2Task achieves 79.6% verified task construction success across these task families. On a matched candidate set, it recovers 29.2% more verified tasks than a construction baseline based on PRs. Historical and reconstructed cases achieve 89.7% aggregate matched outcome agreement under agent evaluation, while reuse of modern bases reduces measured expenditure across the complete pipeline by 10.8%. Four matched studies examine construction stages, semantic review, branch consistency, and resource trade-offs. An industrial deployment further constructs 1,000 tasks from private PR histories and evaluates four models on a fixed 500-task cohort.

cs.SE · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35001

More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation

Yuzhuo Chen, Huafeng Shi, Xinyu Wang, Yulong Xu, Yucheng Wang, Haoqin Hong, Guoxin Zhang, Zehua Ma 等 9 位作者

原文摘要

Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent. But an image can be faithful to the past and wrong for the present. Does visual memory always improve the generated story? We investigate this question through VMem-Bench, a two-track diagnostic study. Track-A measures which references are selected from 92 real films (16,548 segments), before generation and without generator confounds. Track-B compares four retrieval policies with no-memory and gold-informed last-seen controls on 30 causally generated stories (2,824 segments) using a shared generator. Retrieval increases entity recall from 0.559 to 0.628-0.693 and improves similarity to past appearances, but decreases precision from 0.977 to 0.915-0.938 and forbidden-entity avoidance from 0.968 to 0.845-0.898. It can also reinforce obsolete appearances after the story changes them. Conversely, high long-gap recall can arise without memory when the prompt itself supplies the appearance; an appearance-stripping analysis exposes this confound. These results distinguish historical fidelity from current-story correctness and show why retrieval relevance or final-video consistency alone does not establish memory utility.

cs.CV

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1108ACL Anthology · ACL 2026

Text-Guided Multi-Scale Frequency Representation Adaptation

Weicai Yan, Xinhua Ma, Wang Lin, Tao Jin Zhejiang University

原文摘要

Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data distributions. While these methods have shown promising results, they exhibit notable limitations. First, most existing methods operate in the signal space domain, which results in substantial information redundancy. Second, most existing methods utilize fixed prompts or adaptation layers, failing to fully account for the multi-scale characteristics of signals. To address these challenges, we propose the Multi-Scale Frequency Adapter (FreqAdapter), which integrates textual information and performs multi-scale fine-tuning of visual signal in the frequency domain. Additionally, we introduce a multi-scale adaptation strategy to optimize receptive fields across different frequency ranges, further enhancing the model’s representational capacity. Extensive experiments on multimodal models, including CLIP and LLaVA, demonstrate that FreqAdapter significantly improves both performance and efficiency. FreqAdapter improves performance with minimal cost and fast convergence within one epoch.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1136ACL Anthology · ACL 2026

PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning

Rongchuan Mu, Zexin Wang Harbin Institute of Technology, Qianyu Wang, MingHua Ma, Zekun Wang Alibaba Group, Ming Liu Harbin Institute of Technology, Bing Qin Harbin Institute of Technology

原文摘要

Large Reasoning Models (LRMs) excel at complex problem-solving but frequently overlook specific instruction constraints. Existing alignment methods struggle to balance general reasoning with instruction-following (IF), hindered by dependency on teacher models, reward hacking, and reasoning-answer inconsistencies. We propose PARIF, a two-stage curriculum learning framework based on Reinforcement Learning from Verifiable Rewards (RLVR) to enhance both IF and general reasoning capabilities. The framework employs a correctness proxy across different stages to mitigate reward hacking. Stage I employs a dynamic weighting strategy simultaneously to optimize the model’s reasoning paradigm regarding constraints. Stage II introduces Decoupled-GRPO, which builds upon the first stage to enhance the logical consistency between the reasoning process and the final answer, enabling the model to better leverage its optimized reasoning paradigm. To support the framework, we curate 26,000 high-quality instructions featuring diverse constraints. Extensive experiments demonstrate PARIF’s effectiveness: our 7B model achieves a remarkable 21.25% relative average improvement to the original model across six representative IF tasks, while our 8B model outperforms leading models like DeepSeek-V3 on these IF tasks, effectively pushing the Pareto frontier of instruction following and reasoning for models of comparable scale. We open-source our code and models to facilitate future research.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1370ACL Anthology · ACL 2026

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization

Tian Xueyun, MingHua Ma, Bingbing Xu Institute of Computing Technology, Chinese Academy of Sciences, Nuoyan Lyu, Wei Li ByteDance Inc., Heng Dong ByteDance Inc., Zheng Chu Harbin Institute of Technology, Yuanzhuo Wang Chinese Academy of Sciences 等 9 位作者

原文摘要

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers (positives) while ignoring the rest (negatives). We argue that this paradigm discards substantial supervision and exacerbates overfitting, limiting out-of-domain (OOD) generalization. Specifically, we surprisingly find that incorporating negative trajectories into SFT yields substantial OOD generalization gains over positive-only training, as these trajectories often retain valid intermediate reasoning despite incorrect final answers. To understand this effect in depth, we systematically analyze data, training dynamics, and inference behavior, identifying 22 recurring patterns in negative chains that serve a dual role: they moderate loss descent to mitigate overfitting during training and boost policy entropy by 35.67% during inference to facilitate exploration. Motivated by these observations, we further propose Gain-based LOss Weighting (GLOW), an adaptive, sample-aware scheme that exploits such distinctive training dynamics by rescaling per-sample loss based on inter-epoch progress. Empirically, GLOW efficiently leverages unfiltered trajectories, yielding a 5.51% OOD gain over positive-only SFT on Qwen2.5-7B and boosting MMLU from 72.82% to 76.47% as an RL initialization. Code is available at Github.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.253ACL Anthology · ACL 2026

Par-ITA: Benchmarking Seq2Seq and LLMs on a Human-Supervised Parallel Corpus for Italian Hyperpartisan Neutralization

Michele Joshua Maggini Universidad de Santiago de Compostela, Søren Fomsgaard, Michele Maestroni CityNews, Gaël Dias University of Caen Normandy, Pablo Gamallo Universidad de Santiago de Compostela

原文摘要

Neutralizing hyperpartisan content is essential for mitigating online polarization, yet research has largely focused on English. We present Par-ITA, a curated subset from Semeval 2023 task 3, consisting in the first human-supervised parallel corpus for Italian hyperpartisan neutralization of 2,475 paragraph pairs. The dataset is constructed using a rigorous three-stage pipeline: (1) expert-led preliminary selection of LLMs for high-quality generation, (2) human-supervised data production with high editing rates (32–68%), and (3) post-hoc human validation. We establish extensive benchmarks for this task across seq2seq and decoder-only architectures, evaluating standard fine-tuning, Direct Preference Optimization (DPO), and in-context learning. Our analysis highlights that while DPO effectively maximizes neutrality scores in seq2seq models, automated evaluators like GPT-4o-mini exhibit systematic biases, specifically over-penalizing sensitive political topics compared to human experts. Par-ITA provides a foundational resource for non-English neutralization and a reproducible framework for developing high-quality datasets in subjective domains.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.323ACL Anthology · ACL 2026

SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models

Peihua Mai, Xuanrong Gao, Youlong Ding Hebrew University of Jerusalem, Xianglong Du Changan Automobile, Wei Liu Changan Automobile, Yan Pang National University of Singapore

原文摘要

With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-preserving inference methods sacrifice either utility or efficiency, and often require model-specific modifications that limit their compatibility. In this paper, we propose SharedRequest, a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level. The key idea is to obscure sensitive information by mixing original prompts with noisy variants, while grouping semantically equivalent instructions to amortize the inference cost over a large batch of queries with minimal impact on LLM response quality. This design is independent of the LLM architecture, requiring no access to model parameters or architectural modification. Empirical results demonstrate that SharedRequest achieves over 20% higher utility compared to prior differential privacy baselines, and its shared-prompt mechanism reduces query cost by up to 5\times compared to non-batched inference.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.403ACL Anthology · ACL 2026

SCVQ: Sparse-Compensated Vector Quantization for Large Language Models

Zixuan Zhou Beijing University of Posts and Telecommunications, Yujun Diao Beijing University of Post and Telecommunications, Zicheng Kong Beijing University of Posts and Telecommunications, Dehua Ma, Zhenbo Xu, Pei Pei Li, Zhaofeng He Beijing University of Post and Telecommunication

原文摘要

Large Language Models (LLMs) are primarily constrained by memory and bandwidth bottlenecks during deployment. Although Vector Quantization (VQ) has emerged as a promising solution, existing methods incur inference overhead due to massive codebook storage and intensive index lookups. Moreover, these methods typically suffer from non-negligible performance degradation under ultra-low bitwidth regimes. To bridge this gap, we propose Sparse-Compensated Vector Quantization (SCVQ), a novel framework designed for high-efficiency LLM vector quantization. SCVQ introduces a salience-aware weighted K-means clustering scheme with symmetry constraints to reduces codebook size and indexing costs. Central to our approach is a unified structured representation that consolidates outliers, salient weights, and quantization residuals into a single sparse compensation matrix. This design effectively preserves critical model information while leveraging VQ-specific properties to enable efficient custom kernels. Extensive experiments across multiple benchmarks demonstrate SCVQ’s superior performance. Specifically, SCVQ achieves a perplexity of 5.78 on WikiText-2 for LLaMA-2-7B at 2-bit quantization, while delivering a 1.4\times end-to-end inference speedup over existing baselines.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

版本更新 · v5arXiv:2403.05530Google Research

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者

原文摘要

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗