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
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 17:39 · 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 18:06 — 2026-11-08 18:06（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 17:39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 3,292 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 17:37（北京时间）
新论文 · v1arXiv:2611.06553

Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models

Hamid Dashtbani, Alexandra Dmitrienko

原文摘要

Large language models (LLMs) undergo safety alignment to prevent harmful generations, yet they remain vulnerable to jailbreak attacks. Recent work reveals a deeper structural weakness: safety alignment can be highly sparse, such that pruning a small number of safety-critical neurons or ablating a single refusal direction can substantially undermine aligned behavior. In this work, we take the first steps toward strengthening safety alignment such that it is less dependent on sparse model components. We propose Addition by Subtraction, which gradually removes identified safety-critical neurons during finetuning and uses preference optimization to re-establish safety-aligned behavior through other parts of the model. Our results show that the resulting models are substantially more robust to pruning-based attacks. Remarkably, these benefits generalize beyond the white-box attacks motivating our design: Addition by Subtraction improves robustness against other sparsity-based interventions, including refusal-direction ablation, as well as a broad range of black-box jailbreak attacks. The finetuned models also exhibit improved truthfulness while largely preserving general capabilities. Comprehensive experiments across four models from three vendors demonstrate consistent improvements in safety robustness, reducing attack success rates by up to 90% for some attacks.

cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.29300

MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs

Daeyong Kwon, Qiyu Wu, Shinobu Kuriya, Junghyun Koo, Shuyang Cui, Zhi Zhong, Wei-Hsiang Liao, Hiromi Wakaki 等 9 位作者

原文摘要

Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content. However, whether their responses are grounded in the correct temporal regions of the audio remains underexplored. This limitation is particularly critical for music understanding, where key information often occurs as temporally localized events, such as instrument entries and rhythmic transitions. To address this gap, we introduce MusTBench, a reliable benchmark with stem-wise data and music-expert validation designed to evaluate temporal grounding in LALMs through five temporally grounded question-answering tasks. To further improve temporal grounding in existing models, we propose MusT, a novel four-stage temporal optimization recipe spanning music encoder adaptation, LLM adaptation, LLM supervised fine-tuning, and RL-based optimization. Experiments on MusTBench show that existing LALMs face challenges in precise temporal grounding, while MusT consistently improves performance across different LALM backbones and scales. These results highlight temporal grounding as an important challenge in current LALMs and provide a benchmark and training recipe that may support future research on temporally grounded music understanding.

cs.CL · cs.AI · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.16828

Prediction-Intervention Games and Invariant Sets

Linus Kühne, Felix Schur, Jonas Peters

原文摘要

We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable $Y$ from given covariates. The follower then reacts with an intervention on some covariates in the underlying structural causal model to maximize their own objective. The leader knows the intervention targets, but may have limited knowledge of the follower's objective. We call this setup a prediction-intervention game, a special case of a Stackelberg game. Finding an optimal strategy for the leader is generally difficult. To avoid severe performance loss, the leader may base their prediction on the causal parents of $Y$, or more generally on an invariant subset of covariates. We prove, for two common classes of follower objectives, that predictors based on the stable blanket, an invariant subset, are at least as good as those based on the causal parents. We further upper bound the leader's post-intervention risk by a worst-case risk over allowed interventions and strengthen existing distribution generalization results to analyze this bound: we give sufficient conditions under which stable-blanket predictors are worst-case optimal, and show by examples that these conditions cannot in general be dropped. Finally, we discuss practical strategies for settings with known and unknown graph, and test them on simulated and real-world data.

stat.ML · cs.AI · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06522

From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search

Corrado Calamita, Matteo Mendicini, Luca Ferrari, Riccardo Bertamini

原文摘要

Automated failure discovery can be framed as a diversity problem: the objective is to expose distinct ways a system fails rather than a single critical adversarial case. Yet uniform parent sampling provides no way to allocate search effort toward individuals likely to produce durable archive contributions. We study this credit assignment problem in an unstructured Quality-Diversity (QD) archive, testing whether signals available before an individual has reproduced distinguish offspring that merely enter the archive from those still retained generations later. Across a planar-arm benchmark and two robotic-locomotion tasks, the same signals are often associated with entry and persistence in opposite directions. In particular, lineage depth is the clearest such signal, and its persistence discrimination grows with population capacity, which is associated with lower turnover. Biasing parent selection toward the signals with the strongest measured association to survival nevertheless does not improve search: moderate bias matches uniform sampling, and strong bias reduces QD-score.

cs.NE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06519

IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning

Deeraj SK, Sadhana Devarajan, Tanmoy Hazra, Anupam Shukla

原文摘要

Machine unlearning removes the influence of specific training examples to comply with privacy regulations. Full retraining gives strong guarantees but is computationally prohibitive at scale; approximate methods are efficient but lack formal guarantees. SISA (Sharded, Isolated, Sliced, and Aggregated training) achieves certified deletion through data sharding and independent retraining, but random partitioning scatters forget requests across most shards, and isolated retraining degrades utility. We introduce IDSISA (Influence-Distilled SISA), which uses influence functions to concentrate forget-prone samples into few shards and distillation from unaffected shards to recover utility lost to isolation. The deletion guarantee inherited from SISA's retraining step remains exact and requires no probabilistic qualification; the distillation-based utility recovery is a separately quantified, empirically bounded approximation ($ε_{\text{cert}} \leq 0.015$ in expectation). We further formalize certification under sequences of repeated deletion requests, where cross-shard distillation can create dependencies between shards; we prove that a closure-based cascading retraining procedure restores the deletion guarantee to the full aggregated model under any deletion sequence. Experiments on ResNet-18/CIFAR-10, ResNet-18/CIFAR-100, BiLSTM/IMDB, TCN/IMDB, and a fully connected network on Fashion-MNIST show $14-91\%$ better selective forgetting, up to $50\%$ better utility retention in relative terms (with consistent percentage-point gains on the other architectures, where a relative baseline is undefined), and unlearning-time changes ranging from $-6.7\%$ to $+6.4\%$ depending on architecture, relative to SISA.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06518

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu 等 22 位作者

原文摘要

Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target. Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking, while RLHF is difficult to scale and subject to individual aesthetic differences that complicate the calibration of facial, body motion, and chromatic cues across narrative contexts. We introduce EmoReward, a new self-evolving training mechanism that distills evidence reliability from reward traces collected during an actual training run to adaptively guide multi-reward weight allocation in subsequent training by determining which emotional evidence to trust and how much to weight it. EmoReward first plans specific grounding cues from the emotional prompt to guide evaluation, then uses heterogeneous signal primitives to score the generated video during the act stage. Reflective Reward Gating calibrates their contributions through instance-level gates for phase, face confidence, conflict, and subtlety, then renormalizes weights over the active set to produce the sample's fused reward. RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models. Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration for visual generation.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06977

BlockLock: Reproducible LLM Inference with Fixed Batch Geometry

Xiuyuan Qi, Pedro Reviriego, Javier Conde, Shanshan Liu

原文摘要

Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and isolating prefill with fixed-shape decode ({our CoRun-style baseline}) gives up shared prefill compute and pads decode. We present BlockLock, which keeps shared batched prefill and pins only the numerical path of the protected request: it fixes the geometry that the request sees, with {two modes: BlockLock-Rows uses fixed-width rows and retains batched decode of all requests; BlockLock-Pack uses terminal-anchored packing with an isolated dummy segment, then extracts the protected request's KV state for target-only decode. Under a stated per-deployment contract, both modes preserve the target's output bitwise when its companions change.} Across five {dense} models (Qwen3-8B/14B, Llama-3.1-8B-Instruct, and Gemma-3-4B/12B-IT) and three single-GPU deployments (NVIDIA A6000, A100, and H100), we evaluate our approach on both tinyBenchmarks and BFCL{; we also include initial tensor-parallel experiments on two NVIDIA A6000 GPUs. Both modes preserve target sequences and Top20-logit bits in the reported tests.} At equal delivered work, {BlockLock-Rows} reduces latency by 53.5--55.0\% and improves throughput by 115.2--122.2\% relative to vLLM Batch-Invariant; compared with batch-invariant kernels, it needs no custom kernel implementations and constrains only the protected requests.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06508

ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events

Huajian Zhang, Mingyue Cheng, Xingpeng Gao, Xiaoyu Tao, Zhiding Liu, Jiqian Yang, Zhi Li

原文摘要

Accurate electricity load forecasting provides critical decision support for energy procurement, generation scheduling, and supply-demand balancing, contributing to the economic efficiency and operational reliability of power systems. However, future electricity demand can be affected by the complex interplay of multiple events described in Web notices, weather alerts, and event schedules. Their effects vary over time and can reinforce or offset one another, making electricity load difficult to forecast accurately. While existing methods can incorporate context as additional input, how to use the effects of multiple events and their interactions to guide the load forecasting process itself remains to be explored. To address this gap, we propose ElecLoad, a context-aware agent for multi-event electricity load forecasting that adaptively organizes the forecasting process. Specifically, we train ElecLoad to combine historical load with context to analyze each event's relevance to the target load, the timing of its effects, and potential interactions among events. Guided by this analysis, ElecLoad adaptively chooses to forecast the entire forecast horizon directly or to partition it into segments according to changes in event effects. When the horizon is partitioned, sub-agents independently generate initial forecasts for each segment. The main agent then reviews these forecasts, and the sub-agents perform selective refinement guided by its feedback. Experiments on multiple electricity load datasets show that ElecLoad achieves state-of-the-art performance in most evaluation scenarios. Code is available at https://github.com/zhjai/ElecLoad.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06504

NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria

Zainab Afolabi, Nikita Kozodoi, Jack Butler, Babs Khalidson

原文摘要

Multilingual benchmarks for African languages mostly translate generic questions into local languages, measuring linguistic competence but not whether models know facts about Africa. We introduce \naija, a benchmark of factual and statistical questions about Nigeria, authored by native speakers and grounded in authoritative official statistics, with every question available in English, Nigerian Pidgin, \yoruba, Igbo, and Hausa. Answering similar questions for the UK and US yields a country by language matrix that disentangles a language effect (the model knows the fact but degrades in a low-resource language) from a knowledge effect (the fact is absent in every language). Across eight frontier and Nigeria-adapted models, the knowledge effect dominates: English-query accuracy is 49--50\% for the US/UK but 20\% for Nigeria. The language effect is smaller and tracks web representation, degrading from English to \yoruba{} (9 points on Nigeria, up to 24 on US/UK questions). We find scale does not help: the strongest models reach 66--79\% on the UK and the US but none exceed 31\% on Nigerian statistics. Extending to all 54 African countries with our best performing frontier model shows the same profile continent-wide, 96\% on culture and 98\% on politics against 26\% on statistics, so the gap is not specific to Nigeria.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06500

Tools Need Not Speak in Text: Latent Context Compression for Agents

Yuetong Liu, Zhehao Zhou, Yitong Zhang, Haorui Chen, Jia Li

原文摘要

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discrete text representations, limiting the achievable compression ratios. In this work, we challenge the prevailing assumption that agents must consume tool observations as explicit text tokens. To this end, we propose Coca-Cola, a continuous latent context compression model for LLM agents. Coca-Cola compresses tool observations into latent tokens and embeds them into the input embedding space of the agent. We further introduce Action-Preserving Training, which aligns the agent's next-action distributions under full and compressed observations. This trains the compression model to learn action-sufficient latent tokens that retain decision-critical information. Experiments with web-search agents on four QA benchmarks and two model families show that Coca-Cola reduces the agent's token consumption by 70.01%-89.24% and end-to-end runtime by 24.45%-55.97%, while consistently improving task performance. These results suggest that Coca-Cola offers a promising approach for context compression in agents. Our code is available at https://github.com/THU-Agent/Coca-cola.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06491

FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation

Minghao Kong, Zirong Liu, Jianhao Wu, Muyao Chen, Jianxin Wu, Rongjie Wang

原文摘要

Short-interval wireless schedulers must return a complete, feasible beam-and-resource allocation before each execution deadline, and a late or invalid output gives no utility in the current control cycle. Searching longer can increase transmitted traffic, but it may also miss the deadline or leave only an infeasible intermediate solution. We propose Feasibility-Preserving Transactional Refinement (FPTR), which always keeps a validated feasible allocation, the incumbent. Each refinement stage builds a separate candidate and leaves the incumbent unchanged. A candidate replaces the incumbent only if it is complete, passes the feasibility validator before its stage cutoff, and strictly improves the objective; otherwise it is discarded. Four refinement stages use this rule: buffer-aware resource selection, compatibility-group (CG) user sharing, beam-mask rebuilding from remaining demand, and joint reassignment of two resources. On 150 fixed synthetic instances, the full pipeline (Full) raises traffic by 3.83% on average over a lightweight beam-first reference and by 1.79% over its Base constructor. In a separate suite with matched inputs, Full exceeds six independent search baselines (ALNS, tabu search, GA, simulated annealing, iterated local search, and GRASP) by 6.68-8.35%, where outputs later than 100 ms receive zero utility. All 750 Full runs in the internal suite returned feasible allocations, and none exceeded 100 ms. Separating mandatory output construction from optional refinement lets spare computation time improve the allocation without endangering the incumbent. The open-source implementation supports independent reproduction.

cs.AI · cs.AR · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.22968

Certified Circuits: Stability Guarantees for Mechanistic Circuits

Alaa Anani, Tobias Lorenz, Bernt Schiele, Mario Fritz, Jonas Fischer

原文摘要

Understanding how neural networks arrive at their predictions is essential for debugging, auditing, and deployment. Mechanistic interpretability pursues this goal by identifying circuits--minimal subnetworks responsible for specific behaviors. However, existing circuit discovery methods are brittle: circuits depend strongly on the chosen concept dataset and often fail to transfer out-of-distribution, raising doubts whether they capture the concept or merely dataset-specific artifacts. We introduce Certified Circuits, which provide provable stability guarantees for circuit discovery. Our framework wraps any black-box discovery algorithm with randomized data subsampling to certify that inclusion decisions over circuit components--neurons or edges of the model graph, depending on the base algorithm--are invariant to bounded edit-distance perturbations of the concept dataset. Unstable components are abstained from, yielding circuits that are more compact and more accurate. We validate across three architectures (ResNet, ViT, GPT-2) on vision (ImageNet and four OOD datasets) and language (IOI, IOI-Hard, Greater-Than) tasks. Certified circuits achieve up to 56% higher accuracy and up to 80% fewer components, and remain reliable where baselines degrade. Certified Circuits puts circuit discovery on formal ground by producing mechanistic explanations that are provably stable and better aligned with the target concept. Code: https://github.com/AlaaAnani/certified-circuits.

cs.AI · cs.CV · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06486

Model Merging Does Not Require Uniform LoRA Ranks

Zirong Xie, Zainab Afolabi, Nikita Kozodoi, Jack Butler

原文摘要

Model merging combines separately fine-tuned experts into a single model without retraining. Standard practice trains every expert at the same LoRA rank, which couples the rank choice across experts even though each domain has its own best rank. We show this coupling is a property of the merge method, not of merging. We train 36 experts on three domains (mathematics, instruction following, multilingual) at four ranks and three model scales, then merge with six methods at uniform ranks and at each domain's own best rank. Giving experts different ranks costs averaging and utility-based selection nothing, and gains them up to 1.8 pp of multi-domain accuracy, while the conflict-resolution methods are inconsistent and can lose up to 4 pp. The split has a simple cause. Merging keeps only a fixed share of the pooled spectral components, and methods that choose them by size discard many that would have reduced loss. They also tend to discard the same expert: the instruction adapter has the smallest singular values, so it is dropped almost entirely and IFEval falls by 16 to 25 pp. Choosing components by their effect on loss instead keeps all three experts, and leaves accuracy nearly flat across an 8$\times$ rank range (0.7 pp, against 6.7 pp for TIES at 4B scale). Rank can therefore be chosen per expert whenever the merge operator does not select by magnitude.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06481

ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs

Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano Pasquali

原文摘要

Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-construction portability: whether one retrieval procedure, with no construction-specific schema, relation names, or retuning, stays effective when the graph is built differently. We introduce ArcRAG, which induces a query-local graph interface at inference time (the node labels, relation descriptors, and property keys reachable from the entities a question names), plans multi-hop traversals against it, and executes and repairs them as Cypher. We build each of the MuSiQue, HotpotQA, and TriviaQA corpora as a schema-guided graph (typed nodes, a closed relation set, source provenance) and as an open-information-extraction graph (untyped nodes, free-text relations), with the retriever's configuration fixed across them. We compare against a construction-agnostic Direct-Cypher agent, ablate each stage across retry and pass budgets on both graph families, and compare with results reported for prior GraphRAG systems, most of which design retrieval together with their own graph construction. Across the two constructions, we find that retrieval need not be co-designed with the graph: query-time interface induction keeps a construction-agnostic retriever effective when the construction changes, although construction still shapes absolute accuracy.

cs.CL · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.03989

Faces in Things, Faces in Nothing: Probing Face Selectivity in Vision Models with Pareidolia

Qianpu Chen, Derya Soydaner, Rob Saunders

原文摘要

An electrical outlet can look like a face without depicting a person. Face pareidolia is thus a revealing probe of how vision models turn ambiguous visual evidence into category judgments. When a model calls such an object Human, does that answer depend on its face-like arrangement? Using the FacesInThings dataset, we test six vision models, from a vision-only ViT to CLIP and generative vision-language models, with face detectors as a reference. Each face-like region is paired with three controls from the same photograph that lack the arrangement: a background crop, the region with its tiles shuffled, and its average color. A Human answer driven by the arrangement should appear less often on these controls. We also vary how the categories are described. Three findings emerge. First, models respond to illusory faces, but not as people do: face detectors rarely return a face for these regions, yet CLIP ViT-L/14 and two generative models label roughly half of them Human when the categories are described as kinds of face. Annotators, by contrast, read these faces as non-human, such as animal or cartoon faces. For these models, a face is a human face by default. Second, similar Human rates hide opposite behavior. LLaVA-1.5 answers Human less often once the arrangement is removed; Qwen2-VL calls every average-color patch Human and describes a person in each; CLIP ViT-B/32 calls shuffled regions Human more often than real faces; SmolVLM rarely answers Human, but mostly for face-like regions. Third, rewording the categories changes whether Human answers favor the face at all, removing this preference in LLaVA-1.5 and creating it in CLIP. A Human answer is not evidence of a face: vision models can keep giving it after the face is gone.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.24193

PointRAFT: 3D deep learning for high-throughput prediction of potato tuber weight from partial point clouds

Pieter M. Blok, Haozhou Wang, Hyun Kwon Suh, Peicheng Wang, James Burridge, Wei Guo

原文摘要

Key phenotypic traits, such as crop size, volume, and weight, can be estimated non-destructively from point clouds. In practice, however, point clouds of crops are typically incomplete due to self-occlusion, leading to systematic errors when estimating these traits. To overcome this limitation, crop traits can be inferred directly from incomplete point clouds using deep learning-based regression networks. These networks, however, may perform suboptimally, because their predictions do not incorporate prior geometric knowledge of the crop. Such geometric knowledge is often available in structured settings, such as on a potato harvester, where the fixed distance between the camera and the conveyor belt allows tuber height to be derived from the point cloud. To exploit this geometric cue, we introduce PointRAFT, a high-throughput point cloud regression network that incorporates object height through a dedicated height embedding. We hypothesized that this height embedding improves tuber weight estimation from partial point clouds. To test this hypothesis, we collected 26,688 point clouds of 859 potato tubers on an operational harvester, spanning four cultivars and three growing seasons. On a test set of 5,254 point clouds representing 172 tubers, PointRAFT achieved a mean absolute error (MAE) of 11.7 g and a root mean squared error (RMSE) of 17.1 g, outperforming six point cloud regression networks without a height embedding. Requiring only 6.3 ms per point cloud for preprocessing and inference, PointRAFT is fast enough for high-throughput weight estimation on a commercial potato harvester. Beyond potato weight estimation, PointRAFT provides a versatile regression network applicable to a wide range of 3D phenotyping and robotic perception tasks. The code, network weights, and a subset of the dataset are publicly available at https://github.com/pieterblok/pointraft.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06972

KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks

Zi-Jian Cheng, Weiming Wu, Jie Meng, Zhen Peng, Shan Huang, Qun Li, Guobing Wu, Lan-Zhe Guo

原文摘要

Liability adjudication tasks (e.g., legal charge determination) require analyzing event descriptions against domain-specific skills to determine whether a party should bear liability. While Large Language Models (LLMs) have shown promise in this area by leveraging executable skills for interpretable reasoning, existing approaches face three critical limitations: skill libraries become stale as real-world scenarios dynamically evolve, skill descriptions often suffer from a semantic execution gap where LLMs deviate from intended expert logic, and growing skill collections exceed context budgets causing critical skill omission. To address these challenges, we propose Knowledge-Data Dual-Driven Automated Skill Optimization (KDASO), which continuously evolves a skill library through neighborhood-conditioned induction from recent adjudication data, execution-aligned refinement based on LLM trajectory analysis, and context-budgeted routing for scalable skill selection. Experiments across ride-hailing adjudication, legal liability determination, and logical reasoning judgment demonstrate that KDASO significantly outperforms current general-purpose and domain-specific baselines. KDASO further achieves 8.96% improvement when transferring skills to concept-similar scenarios and maintains consistent performance gains through continuous optimization, underscoring the high transferability and stability of generated skills.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06464

Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework

David Gabriel Harispe, Matías Gerard, Pablo A. Kler

原文摘要

Microfluidic droplet generation is critical for many applications, yet efficient device design in high-dimensional parameter spaces remains computationally prohibitive due to complex multiphase flow dynamics. This work presents a unified methodology that couples adaptive surrogate enhancement with simulation-driven inverse design. High-fidelity Volume-of-Fluid simulations provide ground-truth data, while neural network ensembles predict flow regimes and droplet diameters. Ensemble-based uncertainty quantification identifies epistemic uncertainty using consensus levels for regime classification and the coefficient of variation for diameter prediction, revealing that uncertainty concentrates near regime transition boundaries where physics is highly sensitive to parameter perturbations. A physics-informed enrichment strategy targets these critical zones and addresses class imbalances by deploying additional targeted simulations and retraining the surrogates forming the ensembles. A framework that integrates Particle Swarm Optimization for constrained inverse design, balancing accuracy with predictive confidence and physical consistency is therefore proposed. Validation on independent test datasets demonstrates that the enriched ensembles achieve higher accuracy, with the fraction of predictions within the 0-3% error range on droplet diameter nearly doubling, and high-error cases (above 10%) dropping substantially. The inverse design procedure reliably identifies physically realizable configurations meeting target droplet sizes. This approach significantly reduces computational costs while ensuring reliable predictions, offering a framework with potential applicability to the optimization of a broad range of microfluidic systems.

physics.flu-dyn · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.39640

Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies

Dalton Raphael Harmsen, Swier Garst, Thomas van Osch, Zarè Palanciyan, Joaquin Vanschoren

原文摘要

Cross-lingual transfer describes how knowledge in a source language benefits a target language. Measuring it quantitatively requires broad multilingual pre-training, as prior work has done with cross-lingual transfer matrices. We ask whether transfer is predictable from freely available typological features, and whether the prominence of high-resource source languages reflects typology or data quality and quantity. We show that typological databases contain cheap and dense signals about cross-lingual transfer. Our typology-only random forest on a 24-language prior-work transfer matrix scores leave-one-language-out $ρ{=}0.705$ and $R^2{=}0.49$, against $ρ{=}0.62$ for a tuned non-typological control, an increment that a paired bootstrap cannot separate at this scale. When both languages of a held-out pair are unseen, performance degrades to $ρ{\approx}0.41$, so the model interpolates a ground-truth matrix more reliably than it predicts new languages. The signal survives leave-one-script-out and leave-one-family-out protocols, so script and family confounding do not explain the effect. By decomposing the transfer into a typology term and a resource-and-script bias term, we find the best-source ranking sensitive to this bias. Typological features never observe this bias, which makes them a zero-compute screening tool that replaces hundreds of training runs with a model fit. Our code is available \href{https://github.com/dharmsen/typo-x-ling-transfer}{here}.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.23239

AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting

Xudong Jiang, Mingshan Loo, Wengen Li, Mingrui Zhang, Jihong Guan, Shuigeng Zhou

原文摘要

Time-series forecasting is foundational to a wide spectrum of web-scale services, spanning personalized recommendations, energy scheduling, and infrastructure capacity planning. Accurate long-term time series forecasting (LTSF) requires models to capture long-range temporal dependencies while adapting to periodic patterns that vary across variables. Although frequency-aware methods offer a global view of temporal dynamics, they typically rely on inflexible heuristic designs, such as predefined period lengths, manually selected or randomly sampled top-k frequency components, and separate spectral transformations. Consequently, they fail to account for time-frequency heterogeneity, where variables that appear synchronized in the time domain can differ substantially in the frequency domain. Meanwhile, Mamba-based forecasters, despite their efficiency in long-range modeling, introduce frequency information only as auxiliary signals, leaving spectral evidence disconnected from state transitions. In this work, we propose AdaMamba, a novel approach that explicitly internalizes input-dependent frequency information into the modeling of temporal dependencies. AdaMamba comprises an interaction learning module and an adaptive frequency-gated state space module: the former captures cross-variable dependencies and multi-scale temporal context, while the latter generates context-dependent frequency bases and unifies temporal forgetting into a single time-frequency gate that directly modulates state evolution. Extensive experiments on seven public LTSF benchmarks and four domain-specific datasets demonstrate that AdaMamba consistently outperforms state-of-the-art baselines while maintaining competitive computational efficiency.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06452

Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification

Shkelqim Sherifi

原文摘要

Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT), but whether EfficientNet's natural-image scaling hierarchy transfers to medical-image transfer learning at fixed resolution remains unclear. This study evaluates EfficientNet-B0-B7 for four-class SD-OCT classification and accuracy-efficiency trade-offs. Methods: Eight ImageNet-pretrained variants (4.05-64.10M instantiated backbone parameters) were evaluated at 224x224 on the Kermany dataset. Grayscale images were replicated to RGB and processed using model-embedded preprocessing and augmentation. Training comprised frozen-backbone head training followed by partial fine-tuning. Metrics covered classification, discrimination, efficiency, and visual analyses. Results: Test accuracy varied non-monotonically from 95.93% (B0) to 96.95% (B1); B7 achieved 96.73%. B1 had the highest accuracy and Drusen F1 (0.8780), while B7 had Drusen F1 of 0.8720 and the highest Drusen recall (0.9177). Drusen had the lowest F1 across all variants and contributed 82.2% of the summed squared deviation in class-specific F1; class ranking remained Normal > CNV > DME > Drusen. The OCT accuracy ranking differed from the reported ImageNet hierarchy, where B7 ranked first. The accuracy-to-parameter ratio fell from 19.82 to 1.48 percentage points per million total parameters. The final train-test gap had a weak, non-significant association with test accuracy (r = 0.26, p = 0.53). Conclusions: Larger EfficientNet variants did not consistently improve SD-OCT classification. B1 achieved the highest accuracy and Drusen F1, whereas B7 showed a secondary accuracy recovery at greater model size and CPU latency, indicating task and protocol dependent scaling effects. As cross-partition duplicates have not been independently audited, results are conditional on the supplied split.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06449

AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document parsing

Boyu Niu, Yingjie Xiong, Shurui Li, Linhan Pang, Yuntong Zhang, Han Wang, Hao Wu, Kai Zuo 等 11 位作者

原文摘要

Traditional document parsing systems use Markdown as their output representation, which is effective for linear text but does not fully preserve fine-grained spatial structure, table geometry, visual hierarchy, or rendering semantics. We show that HTML is advantageous for heterogeneous and layout-sensitive documents whose representations must remain editable, inspectable, and reusable, and introduce AmbiHTMLBench to systematically study this setting. In this benchmark, given a real-world document, a model must recover executable HTML that preserves its content, organization, and visual appearance. The benchmark contains 1,115 diverse pages with structured annotations and evaluates predictions in two different ways: The objective protocol aligns ground-truth and predicted rendered blocks and measures table fidelity, page-level text error, and a two-dimensional layout consistency; a complementary reference-anchored protocol measures perceived fidelity by aligning LLM judges with human preferences. Across ten primary multimodal systems, the best objective score is 0.8092, while the subjective winner is different, demonstrating that automatic decomposition and human-perceived fidelity capture complementary properties. We further fine-tune a small-parameter expert model and find that task-specific adaptation yields good performance on document-to-HTML reconstruction task. These results position AmbiHTMLBench as a diagnostic testbed for building smarter and more logical document parsing systems.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06445

SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory

Jizhe Zhang, Ang Li, Chenheng Zhang, Yisen Wang

原文摘要

Long-horizon language-model agents accumulate increasingly large interaction histories, making context compaction essential for efficient execution. Existing learned compaction methods often rely on downstream task outcomes or solver behavior, coupling training to specific tasks or agents. We introduce SumOne, a standalone summarizer trained to preserve information in agent histories through masked reconstruction. Given a summary of the expired history, a frozen reconstructor recovers randomly masked portions of the original trajectory; reconstruction quality, combined with a length penalty, provides a task-agnostic reward for optimizing the summarizer with GRPO. This yields self-supervision directly from raw trajectories, without reference summaries or downstream task execution. At inference time, only the lightweight summarizer is retained, enabling plug-and-play context compression for otherwise unchanged agents. We conduct a systematic evaluation of SumOne in long-horizon search and software-engineering tasks. SumOne reduces estimated inference cost by approximately 78\% on DeepSearchQA and 75\% on SWE-bench Verified relative to operating with full context, with absolute decreases of 0.04. The same checkpoint also transfers across downstream models and agent harnesses without additional fine-tuning.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.08686

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation

Ning Yang, Chengzhi Wang, Yibo Liu, Baoliang Tian, Haijun Zhang

原文摘要

Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is therefore irreversible, yet existing methods estimate the corrective signals it relies on, per-head reliability and prompt-level compression sensitivity, online from a single noisy prompt. We argue this is the wrong statistical unit: these signals exhibit far higher cross-prompt regularity than within-prompt signal-to-noise. We introduce \textsc{CompilerKV}, a KV-retention policy whose corrective tables are compiled offline from a calibration corpus, reducing online correction after the standard observation-window scan to $O(1)$ lookups plus a budget clamp. We find that compiled retention tables behave as portable architectural priors: rankings transfer across disjoint corpora on four backbones (mean Spearman $\barρ{=}0.90$), and direct model-to-model table transfer costs only $0.4$--$0.8$ LongBench points on average. At a 512-token budget, \textsc{CompilerKV} attains compressed-SOTA on all four backbones, improving over the strongest prefill-only baseline by $+1.67$ points on average (task-bootstrap 95\% CI $[+1.08,+2.37]$). Pressure regimes amplify the gap: under a fixed $512/32k$ cache ratio, \textsc{CompilerKV} remains the strongest compressed method through 128k RULER ($\sim\!73$ vs.\ FullKV $\sim\!79$, SnapKV $\sim\!38$); on 32k NIAH it reaches $0.89$ vs.\ SnapKV $0.42$; and at 32k input, retaining only $1.56\%$ of the prefill KV, batch-16 serving remains feasible where FullKV is OOM.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.24808

Large-Language-Model Discovery of Quantum LDPC Codes through Structured Concept Evolution

Zidu Liu, Florian Marquardt

原文摘要

Quantum low-density parity-check codes promise low-overhead error correction, but high-performing constructions remain hard to find. Here we introduce structured concept evolution, in which a large language model (LLM) evolves construction programs and their internal search strategies by modifying the finite group, protograph shapes or entry-assignment rule. We search for codes with fewer than $600$ data qubits and check weight at most $12$, optimizing $kd^2/n$ or the circuit-level logical error rate. Our method improves on published lifted-product benchmarks in selected parameter regimes, with exactly certified distances for the leading results. Circuit-level optimization typically yields lower logical error rates than $kd^2/n$ optimization, often despite smaller code distances. With the same evolution framework and step budget, the best LLM outperforms all random-mutation and hill-climbing runs on both objectives. Our results point to LLM-driven program search as an approach to designing general quantum LDPC codes.

quant-ph · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06434

EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking

Jintao Li, Zhiyong Cao, Baihua Xiao, Yu Bai, Börje F. Karlsson

原文摘要

Active embodied question answering requires agents to acquire evidence through viewpoint changes and physical interaction. The central challenge is to avoid undirected interaction: taking plausible actions without specifying what evidence they should reveal for answering the question. Action plans and accumulated histories alone can leave the informational purpose of an interaction implicit. We introduce EviSeek, a training-free framework that makes question-derived evidence demands explicit acquisition objectives, linking observation-conditioned actions and selectively retained evidence to the information the agent seeks. On 3,436 ESI-Bench questions, EviSeek improves accuracy over the Single-model agent by 7.1 percentage points with Qwen3-VL-32B and 3.7 points with Gemini 3.1 Pro, while improving visual-support-weighted accuracy and reducing mean token usage. These findings support making the informational purpose of interaction explicit, with action selection and evidence retention organized around what the agent needs to learn to answer the question.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.06375

Ordinal Credit Assignment: Multi-Step Reinforcement Learning from Comparisons Alone

Hao Yu

原文摘要

Policy-gradient methods need a scalar reward, yet for many tasks no formula captures what we want, while judging which of two outcomes is better is easy. We study reinforcement learning that receives only such comparisons - no reward function, no reward model - in multi-step tasks. Groups of trajectories start from a shared state, and each action is credited by how its reward-to-go compares with those of other trajectories at the same time step. We show the expected update is policy gradient with reward-to-go replaced by its win rate against the population still running at that time, weighted by the chance an opponent is still running; in deterministic environments the update ranks actions by true value and the optimal policy is stable, whereas under stochastic outcomes it prefers actions that win more often rather than those with higher mean. Label noise near ties or from position bias leaves the expected update unchanged; only noise that also flips clear comparisons halves the signal. A critic trained from the same comparisons removes the state confound without changing the expected update. In a pre-registered study over six environments with ten seeds per claim, comparisons cost no detectable performance relative to scalar returns at the same granularity, learning a reward model from the same comparisons is not better, and ten percent of comparisons suffice when spent on a few time points with all pairs. With real LLM judges, comparisons are 7-10 points more accurate than pointwise scores, and the gap grows with the stronger judge. Trained end-to-end with an LLM judge on a requirement the hand-written reward omits, policies satisfy it in all five seeds but land far less often than with oracle comparisons, because the judge is near chance on the near-tied failures dominating early training. Comparisons do not close the gap to PPO with scalar rewards on HalfCheetah.

cs.LG · cs.AI · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06425

D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding

Baoyou Chen, Ruiqiao Mei, Guancong Lin, Tao Song, Weihao Yuan, Qun Liu, Siyu Zhu

原文摘要

Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated target-model hidden states. This forces drafting and verification to run sequentially, limiting speedup even though each block is generated in one pass. We introduce D3D, a standalone diffusion drafter that removes this inter-round dependency. D3D combines blockwise denoising with auxiliary autoregressive supervision to achieve long accepted prefixes without target hidden states. This independence lets D3D draft successor blocks during verification in one packed pass, enabling asynchronous speculative decoding. We progressively prune layers according to their effect on acceptance length to reduce the cost of packed drafting. Removing five of 36 layers retains over 99\% of mean acceptance length across three benchmarks with Qwen3-8B as the target. Across seven benchmarks, D3D averages 5.00$\times$ and 5.71$\times$ decoding speedup with Qwen3-8B and Qwen3-32B targets, compared with 4.03$\times$ and 3.67$\times$ for DFlash. On GSM8K with Qwen3-32B, speedup reaches 7.48$\times$. Code is publicly available at https://github.com/fudan-generative-vision/D3D.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06969

Interactive Backdoor Attacks in LLM-Based Proactive Dialogue Systems

Zhiyang Xia, Yuming Shang, Xi Zhang

原文摘要

LLM-based proactive dialogue systems provide goal-directed support through sustained interaction. Fine-tuning their underlying models on externally supplied dialogue data introduces backdoor risks. Existing LLM backdoor studies primarily focus on eliciting an attacker-specified response upon trigger activation. We present an interactive backdoor attack framework that uses training-data poisoning to steer post-trigger, multi-turn interactions toward an attacker-specified objective. Poisoned fine-tuning dialogues implant a trigger-conditioned guidance-policy bias that ordinary user utterances can activate, without deployment-time prompt modification or further attacker intervention. Specifically, we instantiate three complementary attacks under progressively expanded post-trigger interaction settings: (1) Direct Attack, which targets an immediate response deviation upon trigger activation, retaining the conventional trigger--response setting; (2) Constrained Progressive Attack, which progressively advances the attack objective along a predefined multi-turn trajectory; and (3) Unconstrained Progressive Attack, which extends target-directed steering to open-ended interactions with varied user continuations. Using psychological counseling as a representative setting, experiments on two LLM backbones and two dialogue datasets show that all three attacks effectively achieve their objectives under their respective interaction settings while largely preserving normal utility. Separate defense evaluations show that the tested training-data filters retain nearly all poisoned dialogues, while three post-admission baselines leave substantial residual attack-specific success.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06418

Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness

Kasra Fallah, Rudramani Singha, Hannah Ghanei, Paul Sajda, James Anderson, Erfan Zabeh

原文摘要

Brains and large language models need not be considered equivalent systems to reveal an interpretable commonality: both exhibit high-dimensional, nonlinear dynamics whose behavior can only be modeled imperfectly. This creates a shared challenge whenever we seek to intervene in their dynamics. A controller may either rely on a model identified around a particular operating regime and risk failure as the system moves away from that regime, or explicitly account for uncertainty and a changing internal state. Neurostimulation has confronted an analogous problem for decades. The limitations of fixed, open-loop stimulation have motivated closed-loop and state-dependent approaches that condition intervention on the ongoing state of the neural system. Inspired by this principle, we formulate LLM steering as a feedback-control problem in which the network's internal state, rather than a fixed intervention alone, determines how the system is perturbed. We further account for the mismatch between tractable dynamical models and the nonlinear transformer they approximate through robust control. As one principled realization of this framework, we develop an $H_\infty$-based steering controller that limits sensitivity to disturbances and linearization mismatches. Across multiple steering benchmarks, the controller improves performance over existing baselines, with particularly pronounced gains under out-of-distribution conditions and varying length complexities. Beyond controller performance, we introduce robust steerability, $S_{\mathrm{rob}}$, a pre-deployment measure of tolerance to dynamics mismatch; across model-task pairs, it exhibits task-specific structure and varies systematically with model scale. Beyond robust LLM steering, our measure asks not merely whether control is possible, but how much uncertainty it can survive; a principle that may span artificial and biological neural systems.

q-bio.NC · cs.AI · eess.SY

查看论文
arXiv ↗PDF ↗