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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 18:01 — 2026-11-09 18:01（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：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
新论文 · v1arXiv:2610.37070

Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluation

Yueer Pan, Yuexi Pan

原文摘要

Restricting chain-of-thought (CoT) faithfulness evaluation to correctly answered instances changes the population being measured. We study this selection step in a seven-variable structural causal model and derive the exact observed gap $Δ= \operatorname{Cov}(A, C)/P(C=1)$. The model distinguishes difficulty confounding from shortcut-induced collider bias and states the conditional-independence assumption needed to express the gap through latent response propensities. A protocol review of 18 papers distinguishes answer-correctness restrictions from agreement-based selection, benchmark construction, and training-data filtering. We evaluate four sub-ceiling deployments on arithmetic tasks and observe positive selection gaps in all four. The primary GLM-5.3 run yields a +7.4 percentage-point gap ($n = 1000$, $p < 0.0001$), and pooled Cochran-Mantel-Haenszel analysis gives OR = 1.70 ($p < 10^{-6}$). An assumption-free covariance decomposition assigns 42.8% of the GLM-5.3 gap to between-stratum variation in interventionable-operation count, leaving the majority unattributed. When counterfactual compliance is observable for every instance, evaluating all traces directly estimates population faithfulness without correctness filtering.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37068

Hierarchical Low-Rank Reparameterization for Parameter-Efficient

Rong Huang, Yi Xiong, Yuan-Yuan Cheng, Xiao-Ming Fu

原文摘要

Parameter-efficient fine-tuning (PEFT) methods adapt large models by introducing a small number of trainable parameters. However, we find that these parameters still contain redundancy and can be further compressed while maintaining strong task performance. To this end, we propose a novel hierarchical low-rank reparameterization method. Its core idea is to reorganize the trainable parameters of PEFT methods into an approximately square matrix and then express it via a low-rank decomposition, which can be applied recursively. This forms a multi-level structure with factors compressed level by level, drastically reducing the number of trainable parameters. In our experiments, we combine this reparameterization with LoRA, DoRA, MoSA, and RaSA. We evaluate commonsense reasoning on LLaMA-3.1-8B and Qwen2.5-7B, with additional GSM8K math reasoning experiments on LLaMA-3.1-8B. Under comparable trainable-parameter budgets, our method combined with LoRA or DoRA achieves better performance. Furthermore,when the parameter count of the original methods is compressed by approximately an order of magnitude, our method can still maintain competitive task performance and even surpass the corresponding baselines in average accuracy across the eight commonsense reasoning benchmarks.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37065

Polynomial-Time Solvability of the Mixed Evacuation Problem

Naoyuki Kamiyama

原文摘要

The mixed evacuation problem is a variant of the dynamic transshipment problem where there exist two modes of transportation and we allocate supplies to each mode of transportation in such a way that we can send all the supplies from sources to sinks within a given time limit. It is known that this problem can be solved in polynomial time when the number of sources and sinks is small. In this paper, we prove that the mixed evacuation problem can be solved in polynomial time with the ellipsoid method.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26206

PSPACE-Completeness of the Reachability Relation of Robust Dynamical Systems

Manon Blanc

原文摘要

Dynamical systems are a widely used model of computation and an intuitive representation of many natural phenomena in many applied fields. The last decades have seen an impressive use of computers in studying and analysing them, with several visible theoretical breakthroughs. The question of reachability for dynamical systems is central: given two points, is there a trajectory between them in the dynamical system? Reachability, in particular over the reals, is undecidable in the general case: it is only computably enumerable, even under reasonable hypotheses, e.g. for a computable dynamics in general. But it is known to become decidable, and even lies in PSPACE, under suitably quantified robustness assumptions. In this paper, we focus on PSPACE-completeness results over the reals, in the sense of computable analysis, regarding discrete-time and continuous-time robust dynamical systems. We prove that, under some additional and rather reasonable hypotheses, the reachability relation becomes even PSPACE-complete for both classical and second-order complexity second-order complexity, for an adapted notion of reduction. As a side-effect, we also prove an improvement of an algebraic Ordinary Differential Equations-based characterisation of PSPACE, removing one of the base functions of the algebra. By doing so, we link results from dynamical systems and complexity over the reals, including the models of computable analysis and second-order complexity.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37062

EnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training

Masato Fujitake

原文摘要

Sparse mixture-of-experts (MoE) language-model training can exhibit large loss spikes with Muon-family optimizers. We introduce EnergyCal, a lightweight rule that attenuates routed-expert updates according to the normalized squared Frobenius norm of their finite-step Newton-Schulz directions. EnergyCal leaves the spectral transform unchanged and adds no persistent optimizer state. We evaluate it on a 4B-parameter MoE model. Against a development-selected, lower-learning-rate MuonH recipe, EnergyCal-MuonH reduces mean thresholded loss-spike burden by 99.51% and final geometric-mean perplexity by 4.06%, with a modest throughput cost. With plain Muon at matched nominal learning rate and weight decay, the reduction in mean spike burden averages 95.98% across the two tested exponents, accompanied by small endpoint improvements. These findings support stabilization both with and without Hyperball in the evaluated setting.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.17169

MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis

Anna Oliveras, Roger Marí, Rafael Redondo, Oriol Guardià, Cynthia Ifeyinwa Ugwu, Ana Tost, Bhalaji Nagarajan, Carolina Migliorelli 等 10 位作者

原文摘要

Forecasting anatomical changes such as tumor growth and neurodegeneration is a challenging generative vision task. Morphological evolution is subtle relative to static anatomy, highly patient-specific, and inherently stochastic. Existing methods struggle with several issues: deterministic networks ignore biological stochasticity, while standard diffusion models require computationally prohibitive multi-pass sampling to quantify uncertainty. We propose MUMINS (Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis), an efficient diffusion framework that jointly diffuses a baseline scan and its follow-up residual, summed to synthesize the follow-up scan, while concurrently predicting a spatial uncertainty map, in a single reverse diffusion process. Conditioned on the time interval and relevant metadata, it preserves fine-grained anatomy by dynamically re-injecting the baseline as a soft anchor at every denoising step, and a negative-log-likelihood head learns the uncertainty map to explicitly flag error-prone regions. Designed without organ-specific heuristics, the same architecture is reused across anatomies via separate, dataset-specific retraining. Extensive evaluations demonstrate that dataset-specific retraining of MUMINS matches or outperforms dedicated, domain-specific state-of-the-art methods on lung CT (PNG) and brain MRI (OASIS-3). Project page: https://aolivtous.github.io/publications/mumins.html.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37061

GKS Fully Homomorphic Encryption: Security Analysis

John Graham, Soundes Marzougui, Miloš Pavlović, Vladimir Shpilrain

原文摘要

All traditional encryption schemes share a fundamental operational vulnerability: encrypted data must be decrypted before it can be used. Fully homomorphic encryption eliminates this vulnerability by enabling computation directly on encrypted data, but existing FHE schemes impose substantial practical constraints that limit deployment. This paper presents a formal security analysis of the Gribov-Kahrobaei-Shpilrain (GKS) private-key FHE scheme. GKS requires no bootstrapping or de-linearization, produces bit-exact decryption, supports native encrypted search, and scales to unbounded depth.

cs.CR · math.RA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33771

An actively trained neural operator for near-explicit atmospheric chemistry

Zhi-Song Liu, Wenqing Peng, Ammar Kheder, Risto Makkonen, Michael Boy

原文摘要

Earth-system models simplify atmospheric chemistry into condensed mechanisms, because near-explicit mechanisms such as the Master Chemical Mechanism (MCM) are too costly to solve in every grid cell. Neural emulators could lift this limit, but most advance the chemistry in small time steps and cover only a few species or a reduced mechanism. Here we introduce FNO-MoE, a Fourier neural operator with a mixture of experts that predicts the full near-explicit chemical state over 30 minutes in a single call. The same network also guides its own training, using the disagreement among its experts to select the most informative box-model simulations. At equal cost, this active sampling yields a more accurate emulator than random or evenly spread sampling. Fine-tuning on longer trajectories keeps it stable over multi-hour runs in which models trained on short simulations diverge. The resulting emulator reproduces the evolution of thousands of species with high fidelity, remains accurate for unseen chemical compositions and runs orders of magnitude faster than the numerical solver. These results open a new direction for emulating complex atmospheric systems: neural operators that predict the full chemical state over long windows and choose their own training data. Training under changing meteorology is the next step towards bringing near-explicit chemistry into Earth-system models.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37060

A hyper-reduction strategy for elastoplastic hydro-mechanical problems in partially saturated soil

Alba Muixí, Lluís Monforte, Antonio Rodríguez-Ferran, Sergio Zlotnik

原文摘要

This work proposes a hyper-reduced order model for coupled hydro-mechanical simulations of elastoplastic deformation and water flow in partially saturated soils. These simulations are used to monitor and assess the safety of geotechnical structures such as earthfill dams, where calibration, uncertainty quantification and scenario analysis require solving the same transient model many times for different parameter values. The displacement and the pore pressure are approximated in a field-split reduced basis obtained by proper orthogonal decomposition, and the Galerkin-projected equations are integrated with decomposed cubature rules, one per balance equation, built with the energy-conserving sampling and weighting (ECSW) method. Each residual is split into an affine part and a nonlinear correction: the affine part is computed exactly, at negligible online cost, so that the cubature rule only needs to approximate the correction, which is localized in space. The construction is independent of the constitutive model choices and is implemented in FEniCSx by assembling the original variational forms on the small set of elements selected by ECSW. The method is tested on two- and three-dimensional dams retaining tailings and water, simulating a raise of the dam and the subsequent consolidation phase, with the friction angle, stiffness and hydraulic conductivity of the dam material and the height of the raise as varying parameters. The hyper-reduced model reproduces the displacement and pressure fields with errors below $0.5\%$ with respect to the finite element solution, achieving speed-ups of up to $43\times$ in two dimensions and $77\times$ in three. These performance gains grow with the extent of the plastic yielding, and the selected elements concentrate in the plastified and unsaturated zones, whose size is set by the physics rather than by the mesh resolution.

cs.CE · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32493

K-CLUE: A Segmentation-to-Clustering Framework for Ki67 Cell Typing

Ana Beatriz Vieira, Sara P. Oliveira, Diana Montezuma, João Fraga, Jaime S. Cardoso, Arlindo L. Oliveira

原文摘要

Ki67 is a key marker of tumor proliferation in breast cancer, but its quantification from immunohistochemistry images normally depends on supervised classifiers trained per dataset. We examine the role of frozen pretrained visual representations in annotation-free Ki67 cell typing. To this end, we use K-CLUE, a framework that segments individual nuclei, represents each nucleus with a pretrained encoder, reduces the resulting embeddings with principal component analysis, and separates Ki67-positive from Ki67-negative nuclei using k-means clustering, without task-specific training or manual annotations. Clustering the raw components is highly sensitive to the choice of encoder: across seven encoders, the Ki67-positive F1-score on matched MIST nuclei varies by 44 points, although Ki67 status remains linearly decodable from every representation, with supervised probe AUCs above 0.98. Analysis of the embedding spaces shows that clustering succeeds when DAB-related variation occupies the leading directions of variance. Whitening the retained principal components removes this dependence, reducing the spread across encoders to 1.00 F1-score point. Handcrafted color representations are also competitive, confirming that Ki67 status is strongly reflected in chromatic information, but they require an explicit choice of color space. In end-to-end evaluation, K-CLUE reaches F1-scores of 85.00% and 81.91% for Ki67-positive and Ki67-negative nuclei on MIST, and 79.59% and 81.16% on BCData, outperforming DeepLIIF and IHCScoreGAN on both datasets. These results show that pretrained representations can support annotation-free Ki67 typing when their variance structure is accounted for.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37059

Janus Vehicles: Entity-Centric Threat Modelling of Protocol-Conformant Vehicles under a Malicious-Manufacturer Assumption

Jaeung Franciskus Yoo, Huy Kang Kim

原文摘要

Automotive cybersecurity commonly assumes benign end-product manufacturers and design authorities, focusing on supply-chain threats, external attacks, and compromised network participants observable through misbehaviour. This assumption overlooks malicious-by-design vehicles that remain authentic and protocol-conformant while performing undeclared sensing, communication, or context-triggered actuation. We formulate an Entity-Centric Threat Model spanning three subcomponents. The first, Malign Entity Archetypes, describes four types of malign entity: peer-benign, purpose-malicious vehicles; compromised vehicles; reappropriated genuine components; and imitated vehicles or components. The model exposes two assurance gaps: authenticity does not establish declared-purpose conformance, while malicious functionality can evade detection based on behavioural history or peer-visible evidence. Reappropriated components can remain genuine and retain usable identities or capabilities outside authorised contexts, reducing the effectiveness of signal fingerprinting and certificate-based authentication. To structure this threat space, we introduce a Behaviour-Locus Matrix that maps covert, overt, and concealment actions across hardware, software, and network loci. For peer-benign, purpose-malicious vehicles, we further present a Behavioural Interaction Model that represents how hidden capabilities are contextually activated, realised through actions, manifested within the vehicle and its environment, and potentially observed or concealed.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37058

Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization

Giuseppe Curci, Stefano Simonazzi, Andrea Molinari, Andrea Zugarini

原文摘要

Direct Preference Optimization (DPO) typically relies on preference pairs generated from diverse model pools and ranked by an external LLM judge. The recently proposed delta-learning hypothesis suggests that comparable supervision can instead be obtained from a single pair of models by treating the larger model's response as preferred. We investigate the limits of this approach across model families and scales. We show, both theoretically and empirically, that fixed model pairs introduce systematic, generator-dependent biases that are predictive of the preference label independent of response quality. Consequently, DPO trained on single-pair data consistently underperforms multi-model preference data, despite the larger generator producing higher-quality responses, and we trace this gap to training dynamics consistent with reward hacking on these biases. We further show that simply increasing the number of generators, even without an external judge, is enough to partially mitigate this effect. Our results highlight generator diversity as a critical factor in preference-data construction.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37056

Quantized Edge Inference of a Self-Supervised SAR-Optical Encoder on Commodity x86 Hardware

Christian Sanchez-Leon, Dongming Chen

原文摘要

Self-supervised vision transformers are increasingly used as reusable encoders for Earth observation, but their inference cost on the hardware available in the field is rarely characterized. We deploy a pretrained SAR-optical masked-autoencoder encoder on three commodity x86 nodes, from a low-power CPU without AVX2 to an AVX2+VNNI reference, at FP32, FP16 and INT8 on the CPU and, where present, the integrated GPU, and report latency, energy (RAPL and wall plug) and linear-probe accuracy. Quantization is accuracy-neutral: INT8 changes micro-mAP by only +0.0006, within the seed spread, so precision becomes a pure cost decision. INT8 lowers CPU latency on every node, by 1.45x even on the CPU without AVX2, and CPU energy wherever it is measured, and the VNNI reference (1.53x) suggests a further gain beyond AVX2. The Pareto-optimal device shifts from the integrated GPU, which is 4.38x faster than the CPU on the weakest node, to the CPU as the CPU class improves.

eess.IV · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37055

Blindfold: Keeping the Audit Coin Secret from LLM Agents

Wei Zhu, Meiyun Zuo, Huiping Sun

原文摘要

Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actions and reweighting the audited labels; its validity is meant to rest only on the defender's audit coin. We show that it also rests on a confidentiality property: the coin must not interfere with the agent's view before the action commits, at a time the agent chooses. We call this pre-commit noninterference (PNI) and measure its violation by $D_{\mathrm{A}}$, the total-variation distance between the agent's views under the two coin values. PNI is necessary and sufficient for an unbiased certificate against adaptive agents, the worst-case bias is $(1-\varepsilon)D_{\mathrm{A}}$, and no procedure that sees only audited labels can pay less. Leakage composes across steps, a resource shared across episodes opens a channel of computable size, and raising the audit rate cannot restore validity. On a monitor we built, a silent audit changes no output but adds latency that tool timestamps expose, and the agent can enlarge it. A real LLM agent follows an injection that names a visible audit notice (generic, tool, and timing clauses have no effect); over that channel the plain certificate fails on measured labels and, by a post-hoc analysis, in a live run on a pre-registered schedule, while a silent audit restores it. A fresh coin per audited call closes the timing channel; padding only narrows it.

cs.CR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.30383

Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT

Chakshu Gupta

原文摘要

ML-KEM and ML-DSA compute forward number-theoretic transforms on secret polynomials. Their fixed multipliers, or twiddles, are a documented fault-attack target. This paper characterises the linear map from a secret polynomial to the difference between correct and faulted transform outputs. Each selected twiddle takes a fixed changed field value at every use during one call; zero and nonzero replacements are covered. For one replacement, rank equals the number of butterflies sharing its twiddle, halving by layer from 128 to 2 for ML-KEM and to 1 for ML-DSA. With one replacement per layer, known fault positions, replacement values and a raw transform difference determine every coefficient except the constant and linear coefficients for ML-KEM, or the constant for ML-DSA. Lean 4 certifies this result for both 256-coefficient shapes over fields of characteristic other than two, with nonzero original twiddles. Those coefficients cancel from the difference for every allowed fault set and replacement choice. Seed storage motivates comparing a known correct public key with a released faulty key from the same seed. If only one ML-KEM secret-polynomial transform is affected and all other computations are unchanged, the decoded key difference is a known matrix column times the transform difference. An invertible column entry reconstructs the latter. For ML-DSA, reconstruction and exact candidate counts from paired compressed keys remain unestablished.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2403.18788

Where to Sample: Rethinking ML-Based Malicious Traffic Detection at Terabit Scale

João Romeiras Amado, Francisco Pereira, David Pissarra, Salvatore Signorello, Miguel Correia, Fernando M. V. Ramos

原文摘要

Machine Learning (ML)-based malicious traffic detectors can identify unseen attacks, including in encrypted traffic, but scaling them to Terabit rates remains challenging. Packet sampling, commonly used to meet processing limits, can discard essential behavioral information and render detection ineffective. We present Peregrine, a hardware-software co-designed architecture built around a simple principle: compute features before sampling. Peregrine updates ML features over all traffic at line rate in a programmable switch, then downsamples the feature records sent to software inference. We instantiate this design with two detectors that impose distinct feature-computation requirements on the switch. Across 84 attack traces from three datasets, we show that approximate features computed over all packets can outperform exact features computed from sampled packets. In our evaluation, Peregrine preserves detection effectiveness while reducing feature-record rates by three orders of magnitude - even where pre-feature sampling causes detection to collapse.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37046

Learning to Code the World: Harness Evolution for Compositional 3D Reconstruction

Haoyu Yao, Chenguo Lin, Ruize Du, Yadong Mu

原文摘要

Reconstructing editable and compositional 3D scenes from a real image requires jointly reasoning about geometry, object structure, and spatial relationships. We introduce SceneEvolve, a framework that represents 3D scenes as executable code and improves reconstruction by evolving the harness around a small open-source agent. SceneEvolve combines SceneAct, a compositional semantic action interface built on parameterized primitives, hierarchical composition, and semantic spatial relations, with SceneHarness-RSI, which leverages a stronger teacher agent to iteratively evolve the harness using feedback from development-set reconstructions. Throughout harness evolution, the model parameters, action semantics, and execution backend remain fixed. The resulting harness provides a reusable reconstruction procedure that enables the small open-source model to reconstruct unseen scenes without parameter updates or teacher assistance. Across two in-domain datasets and one out-of-domain dataset, SceneEvolve with the comparatively compact Qwen3.8-27B model improves all four evaluated reconstruction metrics while reducing mean inference time by 47.0% relative to the base model. More notably, despite relying on a substantially smaller model, SceneEvolve achieves 32.3% higher reconstruction quality than the large proprietary GPT-5.6-Sol model, while reducing mean equivalent deployment cost by 59.8%. Furthermore, the harness evolved using Qwen3.8-27B also generalizes to Kimi-K3, achieving comparable reconstruction performance to GPT-6-Astra. The project page is https://haoyu-agent.github.io/SceneEvolve.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37045

AI-Assisted Discovery of CNOT Decompositions for Quantum Permutations on Constrained Topologies

Daniele Lizzio Bosco, Jacopo Cossio, Simone Faro, Francesco Pio Marino, Gabriele Messina, Carla Piazza, Giuseppe Serra

原文摘要

Efficient quantum circuit compilation is challenging for quantum computers, where limited qubit connectivity can introduce substantial overhead in the implementation of logical operations. Recent AI-assisted synthesis methods have shown considerable potential for reducing circuit complexity, but their role in uncovering principles that can guide the design of new deterministic compilation algorithms remains largely unexplored. In this work, we investigate this perspective for the synthesis of quantum permutations into CNOT circuits under constrained qubit connectivity. Using AlphaCNOT as an exploratory tool, we identify a recurring decomposition for remote transpositions that improves on the construction based on adjacent SWAP routing. For two qubits at graph distance $d>1$, the discovered pattern yields a topology-legal implementation using at most $6d-4$ CNOT gates, compared to the $6d-3$ gates required by the corresponding SWAP-based construction. We formalize this observation through a constructive proof to define Global Transpositions, a deterministic synthesis method that searches for a minimum-cost decomposition of an entire permutation into topology-aware logical transpositions. The resulting method subsumes optimal SWAP routing within its synthesis model and provides certified upper bounds on the topology-constrained CNOT cost. Our experiments also reveal circuits that cannot be expressed as concatenations of independently synthesized transpositions. Instead, these circuits exploit intermediate linear transformations that temporarily leave the permutation subgroup and combine partial effects of multiple logical operations, a mechanism we call intermediate CNOT fusion. Our results show that AI-assisted synthesis can support not only circuit optimization, but also the discovery of reusable identities, provable constructions, and hidden mechanisms in quantum circuit compilation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37043

State estimation for a hybrid rigid-continuum space manipulator system

Lorenzo Ticozzi, Patricio A. Vela, Panagiotis Tsiotras

原文摘要

Spacecraft-mounted robotic manipulators can support long-term operability of orbiting assets by conducting tasks such as on-orbit assembly, repair, upgrade, and refueling. In this context, the integration of continuum/soft robotic mechanisms into space manipulator designs promises to reduce stowage volume and mass, as well as to improve operational safety through the inherent mechanical compliance of soft structures. This work presents a novel state reconstruction pipeline for a hybrid soft-rigid space manipulator, in which the distal link is a tendon-driven continuum robot. The estimation problem is formulated as a maximum a posteriori (MAP) inference problem over the hybrid manipulator's configuration, conditioned on discrete, noisy measurements from joint encoders and a vision-based sensing pipeline. The resulting soft-constrained optimization problem is transcribed as a factor graph, providing a compact representation for fusing heterogeneous measurements with the rigid-soft kinematic model. Furthermore, the adoption of the Geometric Variable Strain (GVS) approach yields a minimum-order parameterization of the configuration, a property expected to facilitate model-based feedback control design in future work. The proposed implementation is validated in simulation on a closed-loop trajectory where, for better realism, position measurements for the continuum link are obtained by means of a simulated visual pipeline leveraging synthetic photorealistic images. The state reconstruction accuracy and computational performance confirm the potential of the proposed framework for hybrid soft-rigid robotic applications in orbit.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.34680

QuantForge: Discovering Residual Decompositions for MXFP4 Post-Training Quantization

Qiulin Shang, Zhoutong Wu, Jie Hu, Kun Yuan

原文摘要

Four-bit post-training quantization can reduce the memory demands of large language models, but preserving accuracy under strict MXFP4 W4A4 requires coordinating several design choices. Coordinate transforms change block-encoding errors, which in turn affect the residuals propagated through the network. The useful algorithmic decomposition is therefore not fully known before search. LLM-driven program evolution offers a way to explore these choices, but performance scores alone do not explain which design should change next. We introduce QuantForge, a PTQ discovery system that records competing explanations, selects controls that distinguish them, and checks that successor code implements the resulting conclusions. This residual compilation guides program revisions while retaining useful programs even when their original explanations are rejected. Remeasuring the revised program reveals the next error to address. This process discovers HiRes, a fixed MXFP4 quantizer that shapes coordinates, refines legal code assignments, and recovers errors along attention and MLP paths. Each stage acts on residuals measured after the preceding stage has executed. Across seven tasks, HiRes achieves the lowest seven-model Robust Fit (0.09300) and the lowest quantized Fit-7 at 32B. In matched-budget comparisons of LLM-driven program evolution, each with 240 evaluator calls, QuantForge reaches a held-out transfer target in six of eight runs, compared with three each for textual memory and reflection memory, and one for score-only evolution, despite evaluating fewer new programs. These results show that QuantForge improves the discovery of transferable PTQ algorithms by turning controlled evidence into subsequent program changes. We have open-sourced the QuantForge search framework.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37041

Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewards

Bo Yang, Zishuai Zhang, Weihua Li, Qinnan Zhang, Sijia Wen, Hainan Zhang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming. However, recent studies have shown that RLVR rollouts often collapse onto a narrow set of reasoning trajectories, limiting the explored reasoning space. Motivated by findings that thinking tokens at critical steps serve as critical structural elements in LLM reasoning pathways, we propose Guided-RLVR, a novel approach that augments RLVR with a lightweight controller. The controller strategically injects semantically meaningful steering tokens into the sampling distribution, encouraging the model to approach problems from multiple reasoning perspectives and thereby expanding the exploration space. Experiments on mathematical reasoning and code generation benchmarks show that Guided-RLVR consistently outperforms existing RLVR methods while producing more diverse reasoning trajectories.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37037HF 社区推荐

Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception

Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu 等 13 位作者

原文摘要

Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks that underpin embodied AI and multimodal agents. However, synthesizing targeted, high-quality training data for these tasks remains difficult and costly. Our key insight is that these tasks share an underlying capability, which we call connecting evidence: identifying relevant visual facts, binding them to the correct entities, recovering their relations, and composing them into an answer. Crucially, targeted training data are far easier to synthesize for this capability than for these tasks themselves. To strengthen this capability, we propose EvidenceConnect, an easy-to-implement data synthesis framework that uses zoomed views of related regions within a single image to generate questions requiring comparison, aggregation, or chaining of visual evidence. To ensure quality, a reference answer is retained only when independent VLMs agree on it, and region-ablation tests discard questions whose answer survives the removal of selected regions. We then train base VLMs on the resulting data with RLVR, obtaining Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not tailored to any downstream benchmark, ZwZ2 improves fine-grained and spatial perception, with further gains on embodied spatial reasoning, multimodal long-context understanding, multimodal agent tasks, and general visual reasoning. These results establish EvidenceConnect as an effective framework for supervising evidence connection and suggest that strengthening this shared capability leads to more generalizable multimodal perception.

cs.CV · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37036

GraftRay: Physically Based Mesh Insertion into Gaussian Splatting Scenes via Path Tracing

Jinxin Ai, Matthias Niessner

原文摘要

Inserting virtual objects into scenes reconstructed via 2D or 3D Gaussian Splatting (2DGS/3DGS) is a key capability for content creation, AR, and synthetic data generation. However, realistic insertion requires the object to be seamlessly lit by the scene and, conversely, to cast physically plausible shadows onto it. Existing approaches either harmonize appearance in image space, sacrificing multi-view consistency, or approximate scene illumination with an environment map at the insertion point, which cannot represent near-field area lights such as windows and lamps that dominate indoor lighting. To address this, we present GraftRay, a unified method for physically consistent insertion of mesh objects into indoor scenes represented by either 2D or 3D Gaussians. We recover scene materials and surface normals with diffusion-based priors, and explicitly model spatially-extended emitters, solving their radiance in closed form. A hybrid renderer then jointly path-traces the scene Gaussians and inserted meshes, producing view-consistent shading, interreflections, and soft shadows. On FIPT, GraftRay sets a new state of the art, outperforming recent baselines such as ComGS and EAG-PT in rendering fidelity and shadow accuracy, while maintaining highly competitive rendering efficiency.

cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37033

p-DCIM: A 28nm Probabilistic SRAM DCIM based Ising Machine for Near-Memory Context Selection in LLM-RAG Pipeline

Madhav Vadlamani, Rahul Singh, Yuyao Kong, Haomei Liu, Zheng Zhang, Shimeng Yu

原文摘要

We present a fabricated SRAM DCIM Ising machine that performs set-level context selection for large language model (LLM) with retrieval-augmented generation (RAG). In RAG, the evidence-selection stage is increasingly delegated to repeated language-model reranking, which adds substantial energy to the inference pipeline. We reformulate evidence selection as a quadratic unconstrained binary optimization (QUBO) problem and solve it on a dual-mode digital compute-in-memory (DCIM) macro: the same multiply-and-accumulate datapath computes the embedding-similarity scores that populate the QUBO coefficients and evaluates the per-spin Hamiltonian differences that drive the anneal. The annealing temperature is set by a digital plane-count control along with the SRAM pseudo-read random bit flips, giving graded cooling entirely from on-chip digital configuration. The macro is taped-out in a 28 nm process [0.16 mm2, 0.41 mW] and is proposed to be integrated as part of the logic base-die in hybrid high-bandwidth memory (HBM) and high-bandwidth flash (HBF) stacks in a GPU package, where only the selected passage identifiers return to the host. Replacing the language-model selection pass with the near-memory Ising solver yields a macro normalized selection-energy estimate more than six orders of magnitude lower than the LLM-based baseline and reduces the evaluated total energy per query by 67%, while maintaining comparable token-level F1 on the evaluated examples.

cs.AR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33581

UltraFlash: Accelerating Megapixel Visual Synthesis

Phuc Lai, Anh Nguyen, Phong Nguyen, Anh Tran

原文摘要

Megapixel visual synthesis with latent diffusion models requires operating far beyond the resolutions at which these models are typically trained. Cascade refinement is a leading strategy for this setting: it starts from a base image at a native resolution and progressively upsamples it to the target resolution through multiple refinement stages. Each stage typically performs a pixel-space resolution transition followed by latent-space denoising. While prior acceleration efforts mainly focus on reducing denoising cost, we identify a complementary and underexplored bottleneck: the repeated movement of representations through the VAE. We call these operations pixel-space transitions. In cascade pipelines, intermediate latents are often decoded to RGB, resized, and re-encoded before refinement, while final latents are decoded patch by patch with dense overlap to suppress boundary artifacts. We propose UltraFlash, a transition-efficient approach that accelerates these VAE-heavy operations. UltraFlash has two components. Latent Hyperloop replaces intermediate RGB round trips with a learned latent-space shortcut that approximates the decode-resize-encode transformation without repeated VAE decoding and encoding. Sparse Patch-based Decoding accelerates final reconstruction by addressing patch seams caused by inconsistent GroupNorm statistics and reusing cached statistics across patches, enabling sparse VAE decoding with much smaller overlap. Integrated into a state-of-the-art cascade baseline, UltraFlash reduces 4K generation latency by approximately 2x while improving image quality. These results show that optimizing pixel-space transitions can improve both efficiency and fidelity, offering an effective route toward fast, high-quality megapixel visual synthesis.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.00711

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

Xinshun Feng, Ziqi Miao, Lijun Li, Jing Shao

原文摘要

Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such settings, hallucinations are particularly damaging: a single erroneous claim on a foundational concept can propagate through multi-step reasoning and corrupt entire trajectories. Existing hallucination benchmarks largely operate at the surface level, treating facts in isolation and relying on uniform accuracy metrics that ignore this topological structure. We address this gap with SCHEMA, the first evidence-grounded, topology-aware evaluation framework for hallucinations in scientific agents. SCHEMA automatically constructs scientific concept graphs from benchmark seeds and literature evidence, synthesizes graph-grounded tasks spanning claim verification, multi-hop reasoning, open-ended explanation, and experimental code generation, and evaluates agents with two complementary diagnostics. A trajectory hallucination pipeline audits intermediate reasoning at scale via a topology-weighted severity score, while a multi-agent counterfactual attribution module pinpoints the causal mechanism behind selected failures. SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning. These results indicate that for high-stakes scientific applications, terminal accuracy alone is an insufficient signal of agent reliability, motivating mechanism-level evaluation grounded in knowledge topology. Code is available at https://github.com/circles-post/SCHEMA.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33482

Climate downscaling with likelihood functional flow matching

Zhi-Song Liu, Helmi Toropainen, Ammar Kheder, Michael Boy

原文摘要

Decisions about heat, frost and flooding are made locally, yet reanalyses and climate models resolve tens of kilometres. Generative downscalers add kilometre-scale detail with uncertainty, but are tied to a grid, costly to sample and lack a tractable likelihood. Here we introduce CD-FFM, a functional flow-matching model that treats the high-resolution field as a continuous random field that one model can query at any location and resolution. Its velocity acts pointwise, so spatial variability comes from a noise prior fitted to the observed spectrum and every observation has an exact likelihood. Downscaling ERA5 to 1 km daily temperature over Fennoscandia, CD-FFM lowers the continuous ranked probability score by 27-31% against regression and 12-18% against a forty-times larger neural operator in each of three test years, and outperforms a CorrDiff-style diffusion model while sampling about fifty times faster. The same model transfers to precipitation and makes large kilometre-scale ensembles affordable.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.04883

CLEAR-IR: Clarity-Enhanced Active Reconstruction of Infrared Imagery

Nathan Shankar, Marton Gonczy, Hujun Yin, Pawel Ladosz

原文摘要

This paper presents CLEAR-IR (Clarity Enhanced Active Reconstruction of Infrared Imagery), a novel framework for enabling robust robotic perception in dark environments using active infrared (IR) sensing. IR streams are less susceptible to noise than RGB in low light conditions but are dominated by structured light emitter patterns that hinder high level tasks such as object detection, tracking, and localisation. CLEAR-IR addresses this by reconstructing clean, RGB styled images from emitter populated IR inputs using a dual stream architecture inspired by DeepMAO, enabling standard RGB trained vision pipelines to operate without visible light. Evaluation across object detection, ArUco marker detection, and visual SLAM demonstrates that CLEAR-IR produces reliable perception in conditions ranging from well lit to completely dark, where passive RGB based enhancement methods fail entirely due to the physical absence of sensor signal.

cs.RO · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37026

Interpretable Deep Learning Models for Breast Cancer Diagnosis Using Medical Imaging

Sami Alnawali, Muhammad Atif Saeed, Abdul Hadi, Azka Atiq, Akhtar Jamil, Ahmad Din

原文摘要

Deep learning shows promise for breast cancer diagnosis, but limited interpretability hinders clinical adoption. We benchmark ten ImageNet-pretrained models (ResNet50, VGG19, InceptionV3, DenseNet121, Xception, MobileNetV2, EfficientNet, ConvNeXt, ViT, and Swin Transformer) for benign-versus-malignant classification on the BreakHis histopathology dataset using a patient-level split, and explain their predictions with Grad-CAM, LIME, Integrated Gradients, and LRP. DenseNet121 performed best, with 99.4% test accuracy and an AUC-ROC of 0.999, and significantly outperformed all other models (p < 0.001). Transformer-based models trailed the CNNs. The explanations consistently highlighted nuclei-rich and glandular regions of diagnostic relevance. Combining transfer learning with explainable AI can thus yield accurate, interpretable tools for breast cancer diagnosis.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37022

Crop Yield Prediction Using Regression Models: A Comparative Evaluation of Model Performance

Saptak Das, Arijit Sarkar, Soumik Neogi, Suborno Naskar

原文摘要

Reliable crop-yield prediction can support agricultural planning and resource allocation. This study evaluates five regression models for predicting crop yield from environmental, crop-related, and agricultural management variables. The dataset initially contained 1,000,000 observations and ten variables, with 231 observations having negative target values removed during preprocessing. Categorical variables were represented using one-hot encoding, and Boolean variables were converted into binary values. The models considered were multiple linear regression (LR), random-forest regression (RF), decision-tree regression (DT), ridge regression, and lasso regression. Their performance was evaluated using 80:20 and 70:30 training-testing splits based on the coefficient of determination (R-squared), mean squared error (MSE), and root mean squared error (RMSE). Applying an 80:20 split, LR achieved a test R-squared of approximately 0.9130 and a test RMSE of 0.5008. Applying a 70:30 split, lasso regression yielded the highest test R-squared (approximately 0.9131) and the lowest test RMSE (approximately 0.5008), with performance almost identical to LR and ridge regression. DT also showed improved test performance under the 70:30 split, whereas RF exhibited a substantial gap between training and testing performance. These results indicate that the evaluated linear regression model provides competitive baselines for this dataset. Further experimentation, including validation testing, will help determine the models' performance and predictability.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗