PyTorchKR Papers

최신 논문

총 568,830편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2609.34660v3cs.CL

새로운 연역에 대한 보상: 논리적 추론을 위한 솔버 유도 프로세스 감독

Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning

Logical reasoning remains a major challenge for large language models (LLMs), particularly on structured problems that require precise constraint tracking, consistency preservation, and multi-step deduction. This challenge is especially acute for small-scale LLMs, which are more prone to producing inconsistent, redundant, or brittle reasoning trajectories. Existing approaches for improving logical reasoning largely optimize for final-answer correctness, providing only weak supervision over the intermediate reasoning process. In this work, we propose SPRING: (Solver-guided Process Rewards for Novel LogIcal ReasoNing Step Generation). SPRING uses an SMT solver as a training-time verifier of intermediate reasoning steps to provide process-level supervision. It introduces the notion of a novel reasoning step, namely, a step that is logically valid, consistent with the evolving reasoning state, and not already implied by previously accepted non-contradictory deductions. Based on this solver-based assessment, it designs process rewards that encourage novel inferential progress while penalizing contradictory and uninformative reasoning steps. Evaluation across three logical reasoning benchmarks: ZebraLogic, AR-LSAT, and Knights and Knaves, and four LLMs shows that SPRING consistently outperforms base LLMs, outcome-only reward baselines, and Logic-LM. On ZebraLogic, SPRING improves puzzle accuracy by up to 49.71 and 15.43 points over the base LLM and strongest outcome-only baseline, respectively. On AR-LSAT, it improves overall accuracy by up to 64.43 and 11.39 percentage points over the base LLM and strongest outcome-only baseline, respectively. On Knights and Knaves, SPRING achieves up to 93.14 puzzle accuracy and 96.05 person accuracy.

arXiv:2609.34427v2cs.LG

LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization

Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are predominantly evaluated on small, self-contained textual problems and often commit to a solver-integrated paradigm, limiting their ability to handle the scale and structural diversity of practical optimization workloads. In this work, we propose a practical framework for training open-source LLMs to tackle real-world, industrial-scale optimization. We first show empirically that solver-integrated reasoning, exact combinatorial algorithm, and heuristic search exhibit complementary strengths across different problem structures and scales. Motivated by this, we introduce Strategy-Diverse Reinforcement Learning (SDRL), which trains LLMs as adaptive optimization meta-solvers. SDRL leverages this complementarity through a correctness-gated hierarchical diversity reward that promotes robust exploration across varying strategies and within each strategy, effectively preventing premature strategy collapse. We further introduce a mixed-format training scheme that jointly supports both self-contained textual problems and file-grounded instances. Across comprehensive evaluations, our framework outperforms existing fine-tuned methods and frontier models including DeepSeek-V4-Pro and GPT-5.5, both on average across benchmarks and on industrial-scale optimization tasks. We release our code and training data to facilitate future research https://github.com/tokentideAI/LLMMetaSolver.

arXiv:2609.33239v4stat.ML

Schr\"odinger--F\"ollmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis

Diffusion policies represent multimodal action distributions, but a $Q$-weighted update does not specify how to sample from the resulting target distribution. We propose Schr\"odinger--F\"ollmer Actor--Critic (SFAC), an offline-to-online reinforcement learning (RL) method for Kullback--Leibler (KL)-regularized policy improvement through conditional diffusion. A minimax Bellman critic estimates the action-value function, which defines an exponentially tilted target policy. A Doob $h$-transform expresses this update as a correction to the reference diffusion drift. The target drift is a weighted conditional mean of Brownian-bridge labels. We fit it by weighted regression using endpoints from the current policy and pointwise action-value evaluations. In the small-update regime, the KL-regularized update follows the natural policy-gradient direction, and the Doob correction represents the same local change in the space of diffusion drifts. Under suitable conditions, we derive finite-sample bounds that separate the errors from critic estimation, weighted neural drift regression, and diffusion discretization through a reverse-KL actor bound. The average-performance bound depends explicitly on the comparison coefficients over the policy iterations. Across six D4RL offline-to-online tasks, the final scores of the $Q$-guided bridge-regression implementation exceed its offline initialization on every task and Cal-QL on five tasks. We also compare with offline RL and online-only baselines.

arXiv:2609.33158v3cs.CV

FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs

Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance reported on a single dataset does not capture how models behave under dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging, where robustness, calibration, and fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-Dataset Understanding under Shift), a cross-dataset benchmark evaluating retinal fundus models across vision-only encoder models (VM), vision-language dual-encoder models (VLM), and multimodal large language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public datasets spanning diverse geographies, acquisition conditions, and label protocols. The benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted via LoRA fine-tuning. Results show no model family consistently dominates across tasks and datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual-encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external datasets, particularly in calibration. FOCUS provides a practical framework and public benchmark to assess generalization, reliability, and robustness beyond single-dataset leaderboards.

arXiv:2609.31470v2stat.ML

Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport

Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling or perturbation insufficient for stress scenario generation. Existing outlier synthesis methods typically rely on sparse neighborhoods, low support latent regions, or classifier boundary crossings, which can be heuristic, unstable, and tied to specific modalities or architectures. We therefore propose Sinkhorn Boundary Outlier Generation (SBOG), a structured framework for latent-space outlier generation that couples Sinkhorn optimal transport geometry with distributionally robust boundary modeling. The resulting Sinkhorn-induced support cost guides the sampler toward weakly supported boundary regions, while semantic constraints prevent uncontrolled drift from the intended context, yielding controlled deviations from the in-distribution reference measure rather than arbitrary sparse-region samples. Experiments on time series anomaly generation and image outlier synthesis show that our framework produces informative, semantically controlled outliers and improves downstream robustness evaluation across modalities, providing a foundation for stress scenario generation beyond empirical support.

arXiv:2609.31351v2cs.LG

Progressive Memory Transformer: Memory-Aware Attention for Time-Series

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level contrastive losses and limited temporal neighborhood supervision, but do not explicitly exploit the structural hierarchy. We propose a learning framework that explicitly enforces a structural hierarchy across three scales independently: a local objective for token alignment, a mid-range objective for window-level motifs, and a global objective for sequence-level agreement. Realizing this framework requires the backbone to expose a representation at each scale; we introduce \textbf{Progressive Memory Transformer} (PMT), which augments a transformer with writable, window-aligned memory that exposes the mid-range scale alongside the token and sequence-level representations conventional transformers already provide. Across eight UCR/UEA/UCI classification benchmarks, a cue-retention probe, and forecasting benchmarks, PMT learns representations that probe well at the global, mid-range, and local scales---strong low-label classification (1--5\% labels), competitive forecasting performance across multiple horizons, and quantitative and qualitative evidence that memory states capture mid-range motifs.

arXiv:2609.30906v3cs.CL

ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning

Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promising way to extend LLMs into actionable agents, where tool selection is a critical prerequisite for successful tool use. Existing work often assumes a small or predefined set of tools, leaving large-scale tool selection underexplored. Real-world repositories contain a vast and diverse array of tools, making it difficult for LLMs to effectively search, distinguish, and compose tools under context-length constraints. We identify large-scale tool selection as a new challenge for agentic reinforcement learning, highlighting that existing RL methods for knowledge-based question answering are inadequate for selecting tools while considering compatibility. To address this challenge, we propose ToolSearcher, a novel RL framework for effective multi-turn search and fine-grained optimization in large-scale tool selection. Specifically, we introduce category-constrained tool discrimination to improve the model's ability to distinguish functionally similar tools, event-level search modeling to explicitly optimize the discovery of target tools during multi-turn search, and trajectory-aligned credit allocation to provide fine-grained reward signals for different stages of the search-selection process. Extensive experiments on large-scale tool selection benchmarks demonstrate that ToolSearcher consistently outperforms a set of strong baselines in challenging settings involving iterative search and complex tool composition.

arXiv:2609.30849v2cs.CL

Enhancing Assessment of Self-Consistency in LLM Explanations using Perturbation Strength

Prior work has examined the self-consistency of LLM-generated explanations using surface-level perturbation methods. However, the strength of these perturbations is not explicitly measured and controlled. In this work, we propose an LLM-as-a-judge approach to measure perturbation strength in a unified manner across input and CoT perturbations. We then evaluate the self-consistency in explanations generated from various LLMs under controlled strength conditions, ensuring a fair comparison across perturbation types. Experiments show that our proposed LLM-based perturbation strength measure outperforms other embedding- and probability-based approaches and that input perturbations generally affect LLMs more strongly than CoT perturbations. Our work suggests that judgments about a model's self-consistency is fair only within the same perturbation type.

arXiv:2609.30667v2cs.CV

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms \starwm{} preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors. Code is available on GitHub.

arXiv:2609.30456v2cs.AI

Spectral Feedback for Test-Time Alignment of Protein Diffusion Models

Discrete diffusion models have become leading architectures for inverse protein folding. Test-time alignment guides these models during inference to generate proteins with desirable attributes. Alignment methods for discrete diffusion models often treat inference as a unidirectional process, lacking effective mechanisms for revisiting undesirable token selections. We introduce Spectral Feedback, an algorithm that selects edit-positions in a feedback loop, allowing the model to iteratively correct its own generations. This approach leverages the masking structure of discrete diffusion models by re-masking and re-sampling tokens. While prior alignment methods focus on what token labels to assign to maximize a target reward, we instead treat which tokens to revisit as the central alignment problem. Selecting edit-positions is challenging because edit effects are interdependent: the impact of modifying one token depends on which others are edited simultaneously. We define an edit-set as a set of positions to edit by re-masking and re-sampling the corresponding tokens in a sequence. Motivated by prior work on sparse interactions in biological systems, we find empirically that edit-set value functions for protein inverse folding admit sparse Fourier representations. This structure enables Spectral Feedback to efficiently learn and optimize the value functions for edit-position selection. Spectral Feedback is model-agnostic and can be applied to pre-trained, test-time aligned, and fine-tuned diffusion models without modifying the underlying generative processes. Applied to inverse folding with a protein stability reward oracle, Spectral Feedback increases the proportion of stable proteins by 32.3 percentage points over a pre-trained model, 24.8 over Best-of-10, and 5.8 over a state-of-the-art RL fine-tuned diffusion model.

arXiv:2609.30258v2cs.LG

Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning

Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private observation-action trajectories from per-step policy-learning gradients. The attack exploits two structural signals ignored by prior single-frame methods: (i) cross-time correlation between successive embodied gradients, which we formalize via a conditional mutual-information bound, and (ii) closed-form action recovery from policy-head gradient structure, which we prove exact when standard entropy regularization is sufficiently small. On held-out embodied scenes, TRACE reaches $18.8$ dB PSNR with near-perfect action recovery at $3$-$4.5$ ms per reconstructed frame, dominating the learning-based baseline across all reconstruction metrics and exceeding optimization attacks while running orders of magnitude faster. Further evaluation demonstrates TRACE's broader applicability across recurrent, residual, and compact transformer victim architectures, multi-modal inputs, and larger discrete action spaces. Defense experiments suggest that protecting temporal gradient streams may require sequence-aware privacy mechanisms.

arXiv:2609.30226v2cs.LG

PoEM: Predicting RL Outcomes from Existing Policies

Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as helpfulness, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it possible to predict the policy RL would produce without actually training on that reward? We answer this in the affirmative by introducing PoEM, a framework for predicting RL outcomes using models previously trained on other rewards. First, we build on the fact that if the new reward function can be written as a linear combination of existing ones, then the optimal policy can be expressed as a combination of the existing policies in log-probability space. Surprisingly, even in cases where the rewards are not linearly connected, we observe that policies learned through RL often span an approximately low-rank subspace across rewards. To our benefit, the weights for this combination can be estimated using only the reward or basis policy outputs on the samples. We turn these observations into an algorithm that takes post-trained models and a target reward function, and approximates the target RL policy without any additional RL training. We experimentally evaluate our approach across programmatic and learned rewards for open-ended generation, with additional experiments on math reasoning, tool calling, and image generation.

arXiv:2609.30212v2math.OC

Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems

We characterize, up to logarithmic factors, the optimal higher-order oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximal monotone set-valued operator. We introduce the Anchored Extra-Proximal (AEP) framework, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition. This framework recovers the composite Fast Extragradient method in the first-order setting and yields natural higher-order extensions through Taylor approximations of the smooth operator at the extrapolated point. For every $p\geq 2$, assuming that the $(p-1)$th derivative of the single-valued operator is $L_p$-Lipschitz continuous and the initial distance to a solution is at most $R$, we combine AEP with a bisection line search to obtain a $p$th-order method that attains a tangent residual of at most $\varepsilon$ in $\widetilde{O}((L_p R^{p}/\varepsilon)^{\frac{2}{3p-1}})$ oracle calls. We complement this result with a worst-case lower bound of $\Omega((L_p R^p/\varepsilon)^{\frac{2}{3p-1}})$ for every deterministic algorithm in the $p$th-order oracle model, without imposing any prescribed update structure. For the subclass of smooth nonexpansive fixed-point problems, we further establish a lower bound of $\Omega(\min\{R/\varepsilon, {(L_p R^{p}/\varepsilon)}^{\frac{2}{3p-1}}\})$. By choosing between AEP and Halpern iteration, we match this lower bound up to logarithmic factors, thereby also settling the deterministic oracle complexity of smooth nonexpansive fixed-point problems.

arXiv:2609.28870v3cs.DC

정교한 축출 정책이 실패할 때: LLM 접두 문맥 재사용을 위한 캐시 교체 정책의 재고

When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

Long-running LLM applications and autonomous agents repeatedly send growing context, making prefix caching critical for reducing prefill cost. This raises a fundamental question: do decades of traditional cache-management techniques transfer directly to agentic and conversational LLM serving? We analyze production traces comprising over 20 billion processed tokens and evaluate 14 eviction algorithms across capacity-constrained HBM and large memory-pool settings. We find that simple Least Recently Used (LRU) is surprisingly robust, offering competitive performance against sophisticated traditional policies, though substantial headroom to Belady's optimum remains. The reason is structural: prefix reuse is dominated by the steady pacing of active sessions, making recency an unusually strong predictor for eviction. Nevertheless, prefix caching diverges from traditional workloads in ways that recency ignores, notably the prevalence of single-turn requests, extreme session footprint skew, and highly non-uniform miss costs because attention computation scales with token depth. To close the gap to optimality, we establish several design principles for prefix-cache management: keeping recency as the baseline while incorporating quick demotion to filter one-hit prompts, compute-aware eviction to prioritize expensive misses, and capacity-adaptive eviction granularity. Our traces and simulator are publicly available.

arXiv:2609.28182v2cs.AI

AI 기반 그리드 엣지 협조를 위한 유한 표본 확률적 안전성 인증

Finite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination

Coordinating a large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades. Artificial intelligence (AI)-based control methods such as multi-agent reinforcement learning or imitation learning are promising to this coordination due to their real-time decision scalability. However, system operators still need an independent and rigorous way to decide whether a given AI system is safe enough for deployment. This paper develops a \emph{finite-sample} probabilistic safety certification framework for AI-based grid-edge coordination. The central idea is to reduce the complete input--AI--decision--evaluation workflow to a binary unsafe outcome under an operator-defined safety specification, and then use exact binomial inference to certify the corresponding unsafe operation probability. Given a set of held-out calibration scenarios, the framework returns the tightest one-sided upper certificate and an accept/reject deployment criterion that controls the probability of false safety certification. Because the certification is for the calibration distribution that may \emph{deviate} from the future operation, we further combine the nominal certificate with physically interpretable sample-space adversarial attacks, a concept widely used in AI models to investigate their fragility. Case studies on grid-edge flexibility coordination with 1{,}000-agent AI models (independent parameters) verify the safety guarantee and the value of integrating adversarial attacks into a rolling-window training-certification-deployment flow.

arXiv:2609.27710v3cs.CV

FFM-CP: 퓨샷 계산병리학을 위한 비전-언어 기반 모델의 교차 백본 융합

FFM-CP: Cross-Backbone Fusion of Vision-Language Foundation Models for Few-Shot Computational Pathology

병리학 비전-언어 기반 모델은 질환과 과제에 따라 성능이 달라지며, 어떤 단일 모델도 일관되게 최고 성능을 내지 못한다. 전문가 병리 주석의 높은 비용은 과제별 적응에 사용할 수 있는 라벨 데이터를 제한하기도 한다. 상호 보완적인 사전학습 표현을 결합하는 것은 이러한 한계에 대한 잠재적 접근이지만, 소수의 라벨 예시로부터 효과적인 융합을 학습하는 것은 여전히 어렵다. 본 연구는 퓨샷 학습 설정에서 여러 병리학 비전-언어 모델을 결합하는 프레임워크인 Few-shot Fusion Foundation Models of Computational Pathology(FFM-CP)를 제안한다. 이 프레임워크는 먼저 대응하는 서포트 이미지로부터 추정한 폐형식(closed-form) 직교 프로크루스테스(Orthogonal Procrustes) 변환을 사용하여 이질적인 표현을 정렬한다. 이 정렬은 추가 정렬 네트워크를 학습하지 않고도 모델 내부 특징 기하를 보존한다. 정렬된 공간 안에서 통합 그래프는 서포트 이미지 특징과 시각·텍스트 클래스 프로토타입을 공동으로 정제함으로써 백본 간 정보 교환을 가능하게 한다. 이렇게 정제된 표현은 의미적 클래스 지식과 클래스 내 시각적 변이를 각각 포착하는 상호 보완적인 텍스트-프로토타입 분기와 케이스 검색(case-retrieval) 분기를 지원한다. 각 분기는 모든 순서화된 백본 쌍의 예측을 결합하는 방법을 학습하여, 한 모델로 인코딩된 쿼리가 다른 모델이 표현한 증거를 활용할 수 있게 한다. 우리는 6개의 조직병리학 데이터셋에서 클래스당 4, 8, 16샷 조건으로 3가지 백본 조합을 평가했다. FFM-CP는 54번 비교 중 50번에서 각 융합 집합의 개별 적응 멤버 중 가장 강한 모델보다 더 높은 평균 macro-F1을 달성했다. 이러한 결과는 주석이 제한될 때 상호 보완적인 사전학습 표현의 결합이 조직병리학 분류를 개선할 수 있음을 시사한다.

arXiv:2609.27149v2cs.CV

원격 탐사 변화 탐지를 위한 시간 순서화된 영역 토큰 Mamba와 로짓 공간 확산 모델

Temporally Ordered Region-Token Mamba with Logit-Space Diffusion for Remote Sensing Change Detection

Change Detection (CD) in remote sensing requires jointly modeling bitemporal context and fine-grained spatial details to accurately localize changed regions. While dense attention effectively captures bitemporal relationships, its computational cost limits scalability to high-resolution imagery. In contrast, conventional feature fusion and coarse decoding often struggle to distinguish true changes from appearance variations and preserve object boundaries. To overcome these limitations, we propose Bitemporal Mamba-Diffusion for Change Detection (BMD-CD), a framework that integrates temporally structured state-space modeling with logit-space diffusion refinement. BMD-CD first converts deep bitemporal features into region tokens and organizes them into explicit temporal partitions for bidirectional state-space propagation. It then employs a Learnable Trigonometric Fusion (LTF) module to integrate temporal information and a Conditional Diffusion Decoder that refines coarse predictions in logit space with a short DDIM schedule to generate fine-grained, high-resolution change maps. Extensive experiments on LEVIR-CD, WHU-CD, DSIFN-CD, CDD, and S2Looking demonstrate the effectiveness of the proposed approach. BMD-CD achieves IoU scores of 0.923, 0.957, 0.882, and 0.979 on WHU-CD, DSIFN-CD, LEVIR-CD, and CDD, respectively, and further exhibits strong zero-shot robustness on ValaisCD and B-FLAIR-test.

arXiv:2609.26705v2quant-ph

보손 가우시안 상태는 언제 고전적으로 학습할 수 있는가?

When are bosonic Gaussian states classical to learn?

물리학의 근본적인 질문 중 하나는 양자계에서 고전적 거동이 언제 나타나는가이다. 보손 가우시안 상태(bosonic Gaussian state)는 빛의 고전적 장(field) 거동과 본질적인 양자적 성질을 모두 포착하므로, 이러한 양자-고전 경계를 탐구하기에 자연스러운 환경을 제공한다. 본 연구에서는 학습 이론의 관점에서 이 문제를 다루며 다음과 같이 묻는다. 보손 가우시안 상태는 언제 고전적으로 학습할 수 있는가? 즉, n-모드 보손 가우시안 상태를 고전적인 2n변량 가우시안 분포를 학습할 때 필요한 만큼 적은 샘플과 그만큼 단순한 연산으로 학습할 수 있는 조건은 (있다면) 무엇인가? 우리는 상태의 열적 요동(thermal fluctuation)에 의해 결정되는 학습 가능성의 매끄러운 크로스오버를 규명한다. - 차가운 가우시안 상태는 학습 측면에서 비고전적이다. 공분산 행렬이 $\Sigma\le(\frac12+O(\frac1n))I$를 만족하여 진공 공분산에 가까운 경우, 단일 복사본(single-copy, 즉 얽힘이 없는) 측정 하의 토모그래피(tomography)는 근본적으로 $\Omega(n^3)$개의 복사본을 필요로 하며, 이는 고전적 가우시안 분포를 학습하는 샘플 복잡도 $\Theta(n^2)$를 엄밀하게 초과한다. 우리는 소수 복사본에 대한 얽힘 측정이 허용되더라도 이러한 어려움이 지속됨을 보인다. - 따뜻한 가우시안 상태는 학습 측면에서 고전적이다. 열적 요동이 진공 잡음을 초과하여 임의의 매개변수 $\nu>0$에 대해 $\Sigma\ge(\frac12+\nu)I$로 나타내지는 경우, 단일 복사본 토모그래피에는 $N=\Theta\left(n^2\min(n,1+\nu^{-1})\right)$개의 복사본이 필요함을 증명한다. 이 한계는 타이트(tight)하며, 단순하고 비적응적(non-adaptive)이며 얽힘이 없는 헤테로다인(heterodyne) 측정으로 달성된다. 특히 $\nu=\Omega(1)$인 경우 샘플 복잡도는 $\Theta(n^2)$로 줄어들어 고전적인 경우와 일치한다. 우리의 결과는 보손 가우시안 상태의 학습 가능성에서 나타나는 양자-고전 크로스오버를 엄밀하게 규명하고, 근본 물리학과 통계적 학습 이론 사이의 새로운 연결고리를 드러내며, 실제 센싱 실험에도 시사점을 가진다.

arXiv:2609.26249v2cs.CL

PACE-dLLM: 확산 언어 모델을 위한 신뢰도 절벽 추정 기반 탄력적 블록 디코딩

PACE-dLLM: Elastic Block Decoding via Confidence Cliff Estimation for Diffusion Language Models

Diffusion language models (dLLMs), such as LLaDA and Dream, have become competitive with autoregressive (AR) LLMs in generation quality while supporting native parallel decoding. A standard acceleration strategy is block-wise decoding, where each forward pass predicts a block of length B and commits high-confidence tokens. Confidence-threshold commitment adapts which tokens are accepted, but a fixed B still constrains the prediction scope. Existing horizon policies use manually chosen sizes, volatility statistics, or candidate-boundary scores. We instead use the model's own per-step confidence: in-window confidence typically follows a context-dependent cliff, providing a direct signal for adapting the look-ahead horizon. In this work, we propose PACE-dLLM, which refits this parametric cliff periodically in closed form, sets the next horizon at a shared confidence anchor, and retains confidence-threshold token commitment. Under a saturated-yield abstraction with iid, policy-independent monotone profiles, the oracle horizon is the smallest attaining maximal per-pass yield and improves the asymptotic forward-pass rate when fixed blocks undershoot it with positive probability. On four reasoning and code benchmarks across two open-source dLLM backbones, PACE-dLLM achieves the best average accuracy among the evaluated decoders on both backbones, with average throughput speedups of 5.23x on LLaDA and 3.06x on Dream (up to 8.52x on LLaDA MATH) over the unaccelerated semi-AR baseline, advancing the quality-throughput Pareto frontier.

arXiv:2609.25722v3cs.LG

부호 그래프 사전학습 및 프롬프트 학습

Signed Graph Pre-Training and Prompt Learning

부호 그래프(signed graph)는 엣지가 양수이거나 음수일 수 있으며 방향성을 가질 수도 있는 신뢰-불신 네트워크, 금융 상관관계 시스템, 생물학적 상호작용 그래프 및 기타 여러 도메인에서 발생합니다. 부호 그래프 신경망이 특정 태스크에 특화된 학습(training)을 향상시켰지만, 부호 그래프에서의 그래프 전이학습(transfer learning)은 여전히 미진한 상태입니다. 본 논문에서는 부호 그래프를 위한 선구적인 위상학 기반 그래프 사전학습(pre-training) 및 프롬프트(prompt) 학습 프레임워크인 TopoSIGN을 소개합니다. TopoSIGN은 자기 부호 라플라시안(magnetic signed Laplacian)을 기반으로 구축된 구조적 인코더와 Dowker 복합체 지속성 이미지(Dowker-complex persistence images)를 통해 부호 위상을 요약하는 새로운 지속성 호몰로지(persistent-homology) 브랜치를 결합합니다. 융합된 임베딩(embedding)은 이후 프롬프트 학습 함수로 전달됩니다. 합성 및 실제 데이터셋(dataset)에 대한 실험 결과는 부호 그래프에서 유용한 구조적 정보를 추출하는 TopoSIGN의 효능뿐만 아니라, 제안된 일반 프레임워크의 적응성과 유연성을 입증합니다.