中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (CS.AI) 2026-06-12

Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests

作者:
Ali Arabat↗Mohammed Sayagh↗

arXiv:2606.13449v1 Announce Type: cross Abstract: AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, including code generation proposed through pull requests (Agentic-PRs). For better agent efficiency, developers create instruction files that guide the AI-agents, including how to navigate the project, locate the right components, run tests, respect best practices, and more. In this paper, we investigate the relationship between the creation of these instructions and the performance of AI-agents in creating better pull requests, which have a higher chance of success (i.e., the merge rate), address more complex tasks (e.g., code churn), and require less effort to be merged (e.g., time to merge). To this end, we analyze 15,549 agentic PRs from 148 projects in the AIDev dataset. Using the three dimensions, we compare each project before and after the creation of the instruction files. We find that specifying instructions for AI-agents does not necessarily lead to better results. With the instruction files, 27.7\% of the projects increased their merge rate by at least 20\%, while 26.35\% decreased it. The same observation is seen with the amount of changes (e.g., code churn, number of modified files) and with the efforts to merge an agentic PR (e.g., merge time and number of comments). From a first exploration, we find that projects that managed to increase their merge rate have substantially longer instruction files, which are also well structured into a higher number of sections and sub-sections. Our results motivate the need for research to assist practitioners in framing the development of instruction files as a software engineering activity (aka, Instructions-as-Code).

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-15

Implicit Reasoning for Large Language Model-based Generative Recommendation

作者:
Yinhan He↗Liam Collins↗Bhuvesh Kumar↗Jundong Li↗Neil Shah↗Donald Loveland↗

Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge. Yet reliably invoking this knowledge for GR remains poorly understood. A key obstacle is that LLM-based GR typically represents items with Semantic IDs (SIDs), disrupting LLMs' natural-language reasoning interface because these tokens are unseen by the LLM during pretraining. Existing approaches address this with expensive multi-stage pipelines that ground SIDs and elicit explicit rationales, but offer limited insight into when and why each stage is necessary. In this work, we systematically decompose explicit reasoning training pipelines for LLM-based GR, revealing three key limitations: weakened world-knowledge verbalization, misalignment between SID and natural-language token embedding spaces, and sensitivity to rationale quality, all of which hurt explicit reasoning performance. To circumvent these issues, we propose PauseRec, a lightweight implicit reasoning paradigm tailored for GR. PauseRec is exceptionally practical, avoiding costly reasoning trace acquisition and reasoning alignment training, leading to a multitude of benefits: (1) it outperforms standard explicit CoT methods by up to 6.22%, (2) it reduces training cost by up to 65% GPU hours, and (3) it speeds up inference by up to 71.3%. These results position PauseRec as a lightweight alternative to explicit rationale generation, enabling more effective and efficient LLM-based GR.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.AI) 2026-06-16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

作者:
Tianyi Zhang↗Zhonghao Qi↗

arXiv:2606.16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that describe workflows, tools, resources, and domain conventions. While convenient for inspection and reuse, this design requires the same reusable procedure to be repeatedly injected into the runtime context. We propose Skill-to-LoRA(S2L), a behavior-centric skill representation that replaces runtime skill text with skill-specific LoRA adapters. Rather than compressing the skill document itself, S2L models the behavioral change induced by the skill text: offline, the complete SKILL.md is used to synthesize skill-guided demonstrations; online, the full document is omitted and the corresponding LoRA adapter is dynamically loaded to activate the learned skill behavior. We evaluate S2L with Qwen3.6-27B on a 21-skill subset of SWE-Skills-Bench. Compared with the no-skill and Full Skill Text baselines, S2L improves pass rate by 2.9 and 5.2 percentage points, respectively, while reducing per-step token cost by 6.6% relative to Full Skill Text prompting. S2L matches or improves Full Skill Text on 18/21 skills and the no-skill baseline on 15/21 skills. Control experiments further show that the gains depend on skill-specific adapter alignment: Wrong-LoRA and Shared-LoRA both reduce performance. These results suggest that many procedural agent skills can be converted from runtime instructions into trainable, dynamically loadable behavioral modules. Code will be released upon acceptance.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-12

From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verification

作者:
Rongxin Yang↗Shenghong He↗Siyuan Zhu↗Chao Yu↗

arXiv:2606.13262v1 Announce Type: new Abstract: Recent approaches combining Large Language Models (LLMs) with retrieval-augmented reasoning have shown promise for automated fact verification. To process complex claims, these verification pipelines typically execute multi-stage workflows that coordinate tightly coupled modules, including claim decomposition, evidence gathering, and verdict prediction. However, existing methods optimize individual stages in isolation or rely on fixed heuristics, which limits adaptive coordination among stages and can lead to suboptimal outcomes. In this work, we propose ProFact, an agentic reinforcement learning framework for end-to-end optimization of multi-stage fact verification trajectories. ProFact trains a unified policy to coordinate claim decomposition, evidence seeking, answer generation, and verdict prediction. To address the sparse and delayed supervision provided by final veracity labels, ProFact introduces process-aware rewards that provide stage-level learning signals throughout the verification process. Empirical evaluation shows that ProFact consistently outperforms strong baselines in both verification performance and inference efficiency. These results highlight the effectiveness of process-aware trajectory optimization for multi-stage fact verification.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CL) 2026-06-25

BitNet Text Embeddings

作者:
Zhen Li↗Xin Huang↗Liang Wang↗Nan Yang↗Ting Song↗Yan Xia↗Xun Wu↗Shaohan Huang↗Huishuai Zhang↗Furu Wei↗Dongyan Zhao↗

LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage. BITEMBED converts pretrained LLM backbones into BitNet-style embedding encoders with ternary weights, quantized activations, and lightweight normalization refinement. The converted model is adapted to representation learning through continual contrastive pre-training, followed by supervised contrastive fine-tuning with both similarity-distribution distillation and attention-relation distillation from a full-precision teacher. Beyond quantizing the backbone, BITEMBED further trains output embeddings to support multiple storage precisions meeting different storage needs in various scenarios. Experiments on MMTEB (eng, v2) with Qwen3-0.6B and Gemma3-270M show that BITEMBED is largely comparable to full precision teacher embedders. Moreover, BITEMBED flexibly obtains text embeddings of various precisions, achieving a trade-off between performance and storage cost.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CV) 2026-06-24

Token-to-Token Alignment of Text Embeddings for Semantic Blending

作者:
Saar Huberman↗Ron Mokady↗Or Patashnik↗Daniel Cohen-Or↗

In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derived from these prompts. However, the space of token sequences lacks a consistent accessible structure: semantically similar images may correspond to sequences that differ in wording, ordering, and placement of concepts, while similar token sequences may encode very different semantics. This apparent lack of structure makes it difficult to perform smooth transitions in this space, hindering applications such as image blending and continuous control of edits. We argue that this limitation stems not from the absence of semantic structure, but from misalignment between representations. To address this misalignment, we introduce Token-to-Token alignment, a framework that establishes explicit semantic correspondence between tokens across prompts. Our approach transforms prompts into a structured representation in which semantically corresponding concepts are mapped to consistent positions across prompts, and then aligns their token embeddings based on semantic similarity. Concretely, the method consists of two stages: a structural alignment that rephrases prompts into a shared structured form, followed by an embedding-level alignment that matches token representations across prompts. With this alignment in place, simple linear interpolation becomes a meaningful operation, producing smooth and coherent semantic transitions and enabling applications such as blending and continuous editing. Our results show that text embedding spaces in text-to-image models implicitly encode a continuous semantic structure that becomes accessible once representations are properly aligned, suggesting that semantic control can be achieved by organizing existing representations rather than modifying the generative model.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

作者:
Hoang Phan↗Xianjun Yang↗Yuanshun Yao↗Jingyu Zhang↗Shengjie Bi↗Xiaocheng Tang↗Madian Khabsa↗Lijuan Liu↗Deren Lei↗

arXiv:2510.21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability regression, in which models forget foundational skills after prolonged training without employing regularization strategies. We empirically confirm this concern, observing that open-source reasoning models suffer performance degradation on core capabilities such as perception and faithfulness. While imposing regularization terms like KL divergence can help prevent deviation from the base model, these terms are computed on the current task and therefore do not guarantee preservation of broader knowledge. Meanwhile, commonly used experience replay across heterogeneous domains makes it nontrivial to decide how much training emphasis each objective should receive. To address this, we propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge preservation. Our reweighting mechanism adapts online using short-horizon signals of convergence and instability, shifting the post-training focus away from saturated objectives and toward underperforming or volatile ones. Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning. Extensive experiments on benchmarks using Qwen2.5-VL-3B and Qwen2.5-VL-7B demonstrate the effectiveness of our method, which not only preserves general capabilities but also improves reasoning by enabling more flexible trade-offs among in-task rewards.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CL) 2026-06-18

Output Vector Editing for Memorization Mitigation in Large Language Models

作者:
Ahmad Dawar Hakimi↗Kaiwei Lei↗Isabelle Augenstein↗Hinrich Sch\"utze↗

Large language models memorize and reproduce sequences from their training data, creating privacy, copyright, and security risks. Existing neuron-level mitigation methods equate editing with zeroing out neuron activations, but the activation only controls whether a neuron engages; the output vector is what writes to the residual stream and, through superposition, encodes multiple features. We propose output vector editing, a constrained-optimization weight edit that locates a small set of MLP neurons responsible for a memorized continuation and minimally modifies their output vectors to introduce a distractor in vocabulary space, redirecting their residual-stream contributions while leaving activations unchanged. Evaluating on four models from 360M to 7B parameters (SmolLM-360M, OLMo-1B, OLMo-7B, Llama2-7B), we center on OLMo-7B (whose open weights and pretraining corpus enable systematic mining) and mine 6831 memorized sequences, achieving up to 87.9% suppression. The 2.7$\times$ gap over zero ablation on the same located neurons shows the suppression comes from the output-vector edit, not localization alone. Four edit modes span a spectrum from aggressive suppression to minimal redirection; in ensemble they cover 96.5% of memorized sequences, while our recommended single-mode configuration reaches 81.5% with no catastrophic locality failures. We further identify a mechanistic boundary at ${\sim}14%$ of sequences unreachable by MLP-only editing; while these failures are not attention-driven overall, ablating the top contributing attention heads recovers 60–64% of them, with stronger recovery on continuations that copy tokens from the prefix, positioning attention as a complementary fallback rather than a primary mechanism. Edit mode ordering and the success-locality trade-off transfer across all four models, with success rates scaling with model size rather than family.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.LG) 2026-06-16

We Need Explanation Cards to Connect Explanation Algorithms to the Real World

作者:
Eric G\"unther↗Bal\'azs Szabados↗Kristof Meding↗Gunnar K\"onig↗Sebastian Bordt↗Ulrike von Luxburg↗

arXiv:2606.16786v1 Announce Type: new Abstract: Algorithmic explanations are intended to help stakeholders understand opaque algorithmic decisions, but in practice, they often fall short. First, the meaning of algorithmic explanations is often not what one might intuitively expect, so expert knowledge is required to interpret them correctly. Second, recent work has shown that popular explanation algorithms are uninformative about the behavior of complex decision functions. Together, these issues create a gap between what explanations appear to convey and what they actually provide. In this work, we propose Explanation Cards for Explanation Algorithms, which augment standard explanations with complementary information about robustness and validity, as well as clear instructions for interpretation. The complementary information can render otherwise uninformative explanations practically useful, while also helping to detect cases where they are not. Importantly, the interpretation instructions in explanation cards shift responsibility from users to providers: Rather than expecting users to recognize what can and cannot be concluded from an explanation, providers must make this explicit upfront. Using counterfactual explanations and SHAP as examples, we demonstrate how providers can construct explanation cards and that these cards provide users with the guidance needed for sound interpretation. We further argue that explanation cards offer a practical means of operationalising the explainability provisions of the EU AI Act. Overall, explanation cards are a significant step toward making explanation algorithms fit for real-world use cases.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CL) 2026-06-18

ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"

作者:
Zhongyi Zhou↗Kohei Uehara↗Haoyu Zhang↗Jingtao Zhou↗Lin Gu↗Ruofei Du↗Zheng Xu↗Tatsuya Harada↗

Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data generation. We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients", and then synthesizes corresponding user queries. This "answer-first" approach led to ToolGrad-500, a dataset generated with more complex tool use, lower cost, and almost 100% pass rate. Experiments show that ToolGrad models outperform those trained on expensive baseline datasets and proprietary LLMs. The ToolGrad source code, dataset, and models are available at https://github.com/zhongyi-zhou/toolgrad.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-19

AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

作者:
Faqiang Qian↗Kang An↗Weikun Zhang↗Ziliang Wang↗Xuhui Zheng↗Liangjian Wen↗Yong Dai↗Mengya Gao↗Yichao Wu↗

arXiv:2509.25148v2 Announce Type: replace Abstract: Post-training alignment of large language models often combines supervised fine-tuning (SFT) on expert demonstrations with reinforcement learning (RL) from preference or verifiable feedback. SFT provides a useful behavioral anchor but can overfit to static demonstrations, whereas RL encourages exploration but may drift from expert behavior or exploit imperfect rewards. We propose AAPA (Adversarially Anchored Preference Alignment), a plug-in framework that augments existing post-training objectives with a sentence-level adversarial anchoring signal. AAPA compares policy rollouts with offline, pre-collected expert responses using a fixed lightweight discriminator, and therefore requires neither online teacher inference nor discriminator co-training during policy optimization. The same anchoring term can be added to SFT, GRPO, and CHORD while preserving their original training pipelines. Experiments on instruction-following benchmarks show that AAPA consistently improves the corresponding base objectives across model scales. In particular, the staged AAPA configuration improves over a strong GRPO baseline by 5.77\% on \texttt{Qwen3-0.6B} and 3.75\% on \texttt{Qwen3-4B}. Further analyses on response length, log-probability distributions, and discriminator variants suggest that adversarial anchoring provides a stable semantic grounding signal for preference optimization. Code is available at \url{https://github.com/IsFaqq/AAPA}.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-16

QPILOTS: Efficient Test-Time Q-Steering for Flow Policies

作者:
Yifan Ruan↗Chenyang Cao↗Andreas Burger↗Ali Pesaranghader↗Kaveh Kamali↗Jaehong Kim↗Nandita Vijaykumar↗Alan Aspuru-Guzik↗Igor Gilitschenski↗Nicholas Rhinehart↗

arXiv:2606.14801v1 Announce Type: cross Abstract: Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy extraction requires exploiting the critic's action gradient, yet directly backpropagating this signal through a multi-step denoising process can be numerically unstable. Existing methods work around this either by discarding gradient information, distilling the policy into a simpler one-step actor, or repeatedly fine-tuning the denoising policy as the critic improves. We propose QPILOTS, a method that leaves the original policy unmodified and steers the denoising process at inference time. At each denoising step, instead of evaluating the critic on the noisy intermediate action where critic predictions are unreliable, we first project that intermediate state to an estimate of the final clean action and compute the critic gradient there. We introduce two variants: QPILOTS-U uses a fast single-point approximation, while QPILOTS-M draws differentiable posterior samples via a learned auxiliary network. On a standard offline-to-online RL benchmark, QPILOTS achieves the best aggregate performance, reaching an average success rate of 90% across 50 tasks. We also apply QPILOTS to steer a large, frozen, pretrained Vision-Language Action (VLA) foundation model, outperforming or matching prior inference-time approaches across six manipulation tasks in simulation.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CL) 2026-06-16

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

作者:
Jiangze Yan↗Yi Shen↗Wenjing Zhang↗Jieyun Huang↗Zhaoxiang Liu↗Ning Wang↗Kai Wang↗Shiguo Lian↗

Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream tool failures, noisy observations, or reasoning errors rather than its own contribution. This causally entangled credit can lead agents to discard useful evidence or preserve irrelevant information. We propose HiMPO, a Hindsight-Informed Memory Policy Optimization framework for assigning less-entangled credit to memory-writing actions in long-horizon agents. HiMPO first estimates the local utility of a memory update by comparing the task-relevant information recoverable from the previous and updated memories under the same pre-write state. It then uses hindsight relevance as a bounded retrospective filter that attenuates memory credit when local utility is not supported by the target outcome. The resulting memory-specific advantage is applied only to memory tokens, while trajectory-level rewards optimize the rest of the agent behavior. Across judge-based open-domain tasks and objective compressive-memory QA, HiMPO improves over strong memory-based and RL-based baselines while preserving compressed-context efficiency. Controlled interventions further show that HiMPO reduces blame leakage from tool-induced errors and improves attribution fidelity of memory updates.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.LG) 2026-06-12

How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?

作者:
Julia Kostin↗Kasra Jalaldoust↗Elias Bareinboim↗Samory Kpotufe↗Fanny Yang↗

arXiv:2606.12680v1 Announce Type: new Abstract: Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-based domain generalization has shown how shared causal structure between domains can induce invariant predictors, e.g., models on a subset of features which have stable risk across structured domain shifts. However, the extent to which such population-level causal invariances can lead to gains in finite-sample settings remains underexplored. In particular, in practice we often have access to a few labeled target samples, a setting called supervised domain adaptation (sDA). In this paper, we explore when (full or partial) causal knowledge can provably improve supervised domain adaptation. As a first step, we study linear regression, where full or partial causal knowledge specifies a collection of invariant or possibly invariant feature subsets, each yielding a source-trained candidate predictor. We derive matching upper and lower bounds showing that finite-sample gains are governed by the target-risk margins separating the candidates, together with the finite-source estimation error. When these margins are sufficiently large relative to $n_Q$, an adaptive aggregation procedure can match the best candidate predictor while avoiding negative transfer relative to target-only learning. On the other hand, when the margins are too small, no algorithm can reliably exploit the candidate collection to obtain faster finite-sample rates. We further connect these margins to structural shift magnitude in linear SCMs and validate the theory on real-world causal benchmarks.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-12

Transformer-Guided Graph Attention for Direct Cardiac Mesh Reconstruction: A Structural Digital Twin Framework

作者:
Abhishek H S↗Akash Ganamukhi↗Abhimanyu Suresh↗Aditya G Hiremath↗Prasad B Honnavalli↗Adithya Balasubramanyam↗

Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting those models into clinical use keeps running into the same wall: mesh generation is slow, messy, and frustrating. The standard workflow – segmenting the image, running Marching Cubes, and then manually cleaning up the result – is time-consuming, inconsistent across operators, and demands specialist knowledge most clinical teams do not have. We take a fundamentally different approach. Instead of treating segmentation and mesh generation as two separate problems, we train a single end-to-end network that goes directly from a raw 3D medical image to a smooth, simulation-ready cardiac surface mesh. The core is a 3D Swin Transformer encoder-decoder that extracts volumetric features from CT or MRI volumes, paired with a Graph Attention Network (GAT) head that iteratively deforms a template mesh to fit the patient's cardiac boundary. We tested on the MM-WHS 2017 benchmark using both CT and MRI. Segmentation scores were competitive (Dice of 0.84 on CT, 0.83 on MRI), but the primary focus is mesh quality: mean Chamfer distance of 1.8 mm, with 95th-percentile surface distance below 5 mm. Every mesh is produced in a single forward pass – no Marching Cubes, no smoothing filters, no manual cleanup. We argue that for cardiac digital twin pipelines, geometric fidelity and topological correctness matter more than pixel-level Dice scores. By removing the post-processing bottleneck, this approach makes patient-specific cardiac simulation substantially more accessible for clinical use.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-19

Thermodynamic Measure of Intelligence

作者:
Ishanu Chattopadhyay↗

arXiv:2606.20231v1 Announce Type: new Abstract: Can intelligence be measured? We propose that intelligence can be defined as the lawful amplification of rare but valid futures: a system increases the probability of outcomes that would be unlikely under passive dynamics but remain admissible under the constraints of the domain. We start with the premise that an intelligent system must model the world and its own place within it. Because the system is part of the world it models, this leads naturally to recursive self-simulation: the system represents futures in which its own actions are part of the trajectory. Our central results give a necessity statement and a conditional near-sufficiency statement connecting this architecture to a precise thermodynamic measure of lawful amplification of rare-valid futures: high rare-valid lift is impossible unless the internal simulation identifies rare-valid futures with high fidelity; conversely, when rare-valid fidelity is high and the simulation contains an effective policy, the achievable lift approaches the actuation-limited optimum. Thus recursive self-simulation is not merely a plausible feature of intelligence but, under the stated assumptions, is necessary and nearly sufficient for high thermodynamic intelligence. The resulting framework makes intelligence measurable on a universal scale, from passive matter and feedback controllers, large language models, and humans as text generators to Maxwell-demon-like information engines.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.LG) 2026-06-24

The Cost Geometry of Belief: finite-resource inference under noisy observation

作者:
Laurent Caraffa↗

arXiv:2606.21585v2 Announce Type: replace Abstract: A finite machine's digital twin of a system observes the territory through finite, noisy sensors; we model its coherent output as a belief, a probability density over states, the Bayes posterior, never a point. Certainty, the perfect twin, is denied twice, by observation and by physics, both read off the Fisher information. To make this finiteness geometric, we model what it costs to change a belief: a belief-cost geometry, optimal transport in Wasserstein space reweighted conformally by Fisher information. The framework rests on two posed commitments: that revision cost is a scalar price on transport (the arena), and that the price is honest: one nat costs the same length everywhere. Honesty selects the Fisher reweighting because transport demotes the Fisher information from the metric ruler of distinguishability to the slope of entropy, the move that sets transport apart from Fisher-Rao. From these two postulates, three results follow on the conformal class (essentially location-scale), all invariants of one change of cost unit. A wall: a well-posed inference rejects certainty to infinite distance as soon as the cost dominates the Fisher information (necessity conjectured beyond power laws). An honest family: the eikonal price where each nat the same length everywhere, is equivalent to proportionality U=cJ, the Fisher family. A rigidity: these geometries are hyperbolic, and the Stam bound crowns the Gaussian, the most hyperbolic location-scale belief; -1/4 is one image of a relativity of cost. The cost of reaching a given precision then has a geometric cost floor diverging at certainty. Thermodynamics fixes the cost unit and motivates the framework; the results are geometric, in nats.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.AI) 2026-06-24

LaGO: Latent Action Guidance for Online Reinforcement Learning

作者:
Kuan-Yen Liu↗Ren-Jyun Huang↗Ti-Rong Wu↗

arXiv:2606.24669v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be unreliable in practice. This paper proposes Latent Action Guidance for Online Reinforcement Learning (LaGO), a framework that uses a pretrained LLM as a latent action prior to softly guide online policy optimization, rather than treating the LLM as an explicit planner or controller. Experiments on both a discrete-control benchmark, CLEVR-Robot, and a continuous-control benchmark, Meta-World, demonstrate that LaGO consistently improves both reward and success rate over Vanilla PPO. In particular, LaGO increases the average success rate from 15.1% to 27.2% on CLEVR-Robot and from 2.7% to 15.2% on Meta-World. Our analysis further shows that stronger pretrained LLMs provide more effective guidance, suggesting that LLM knowledge can improve planning and online decision-making.

阅读与讨论 → 访问原文 →
19.
arXiv (math.PR) 2026-06-16

On the empirical spectral distribution of matrix perpetuities

作者:
Bartosz Ko{\l}odziejek↗Kamil Szpojankowski↗

arXiv:2605.31054v2 Announce Type: replace Abstract: We study matrix perpetuities, that is, solutions to affine fixed-point equations of the form \[ \mathbf{X} \stackrel{d}{=} \mathbf{A}\,\mathbf{X} \,\mathbf{A}^\top+\mathbf{B},\qquad (\mathbf{A},\mathbf{B})\mbox{ and }\mathbf{X} \mbox{ are independent}, \] with particular emphasis on the empirical spectral distribution of the solution. We first establish existence and uniqueness results by relating the problem to classical vector perpetuities, and then develop tools that preserve the matrix structure under orthogonal invariance. For positive semidefinite, orthogonally invariant models, we obtain power-law tail asymptotics for the expected empirical spectral distribution and show that the tail is governed by the largest eigenvalue. We also prove that, in the subcritical regime, the expected empirical spectral distribution of matrix perpetuities converges weakly, as the dimension tends to infinity, to the distribution of the corresponding free perpetuity. Our results are illustrated by matrix Beta prime perpetuities, for which explicit limiting spectral distributions are available.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-16

GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness

作者:
Zhiyuan Ye↗Xiangyu Zhou↗Ji Qi↗Hao Zhang↗Yi Zhou↗

arXiv:2606.14865v1 Announce Type: cross Abstract: Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start. This paper asks whether the order in which parameters become optimizable can affect the final robust solution, even when the final architecture or computation budget is controlled. We propose GRAPE, Guided Parameter-Space Evolution, a training framework for compact adversarial robustness. GRAPE combines parameter-space stabilization with progressive hidden expansion: it stabilizes robust optimization in the currently exposed space, gradually releases new optimizable dimensions, and uses an adversarial spectral utilization score to guide newly released capacity toward high-pressure modules. In contrast to fixed-structure AT, GRAPE treats robust model learning as a process of progressive parameter-space exposure and evolution. Under the standard $\ell_\infty$ threat model on CIFAR-10, with fixed-structure ResNet-18 AT as a controlled reference, GRAPE improves PGD-20 robust accuracy from 51.70% to 56.94% at a nearly matched computation budget with a FLOPs ratio of 1.009x, while reducing parameter count by about 21.4%. A sequential grow variant with the same final ResNet-18 architecture reaches 56.52% PGD-20 robust accuracy, indicating that the gain is not only due to final architecture differences but also to the parameter-space exposure path. These results suggest that guided parameter-space evolution can yield compact and robust parameter configurations under matched computation.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.LG) 2026-06-17

Robust Local Polynomial Regression with Similarity Kernels

作者:
Yaniv Shulman↗

arXiv:2501.10729v3 Announce Type: replace-cross Abstract: Local Polynomial Regression (LPR) is a widely used nonparametric method for modeling complex relationships due to its flexibility and simplicity. It estimates a regression function by fitting low-degree polynomials to localized subsets of the data, weighted by proximity. However, traditional LPR is sensitive to outliers and high-leverage points, which can significantly affect estimation accuracy. This paper revisits the kernel function used to compute regression weights and proposes a novel framework that incorporates both predictor and response variables in the weighting mechanism. The focus of this work is a conditional density kernel that robustly estimates weights by mitigating the influence of outliers through localized density estimation. The proposed method is implemented in Python and is publicly available at https://github.com/yaniv-shulman/rsklpr. The population analysis quantifies the bias induced by density-based robust weighting, and the reported experiments show lower empirical bias than iterative robust LOWESS while remaining competitive with standard LOWESS. This advancement provides a promising extension to traditional LPR, opening new possibilities for robust regression applications.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.LG) 2026-06-16

A Biased Nonnegative Block Term Tensor Decomposition Model for Dynamic QoS Prediction

作者:
Wenjing Liu↗Yujia Lei↗Qu Wang↗

arXiv:2605.04813v2 Announce Type: replace Abstract: With the rapid development of cloud computing and Web services, Quality of Service (QoS) has become a key criterion for service selection and recommendation. Tensor latent feature analysis provides an effective way to model multidimensional QoS data, and most existing QoS prediction methods are mainly based on Canonical Polyadic (CP) decomposition or Tucker decomposition. However, constrained by their inherent structural properties, these methods cannot accurately capture the complex and dynamic dependencies in user-service interactions, which limits their prediction performance. To address this issue, this paper proposes a dynamic QoS prediction framework based on the Biased Nonnegative Block Term Tensor Decomposition Model, termed BNBT. Specifically, the proposed framework is developed from three aspects: (1) block term tensor decomposition is employed to enhance the representation capability of latent feature learning; (2) linear bias terms are incorporated to further improve prediction accuracy; and (3) a tensor-oriented single-element-dependent nonnegative multiplicative update algorithm, called SLF-NMUT, is designed for efficient parameter estimation. Extensive experiments on real-world QoS datasets demonstrate that the proposed BNBT framework consistently outperforms several state-of-the-art QoS prediction methods in terms of prediction accuracy.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CL) 2026-06-16

Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

作者:
Yanming Zhang↗Yihan Bian↗Jingyuan Qi↗Yuguang Yao↗Lifu Huang↗Tianyi Zhou↗

While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs, allowing selective refinement without discarding previous answers and generating another from scratch. While this property more closely aligns with how humans correct mistakes by iterative local refinement, existing MDMs do not support multi-turn masking and denoising. We propose Reflective Masking (RM), which elicits such an intrinsic reasoning capability in MDMs via lightweight post-training. RM provides a native test-time scaling, where an MDM iteratively revisits and revises its prior outputs based on evolving context. To exploit insights from previous turns like AR reasoning, we further introduce History Reference, a parameter-free mechanism that leverages intermediate denoising states during revision. Our approach requires no architectural changes and is easily applicable to existing MDMs. Across diverse tasks and modalities, including text generation, Sudoku, and image editing, Reflective Masking consistently outperforms standard masking-based baselines and demonstrates strong generality, positioning RM as a fundamental primitive for reasoning on MDMs.

阅读与讨论 → 访问原文 →
24.
arXiv (quant-ph) 2026-06-19

QPU-scale randomized benchmarking via Bell-pair injection

作者:
Haripriya Pettugani↗Mar\'ia Aguado-Y\'a\~nez↗Astryd Park↗Daniel Bultrini↗James R. Wootton↗

arXiv:2606.20123v1 Announce Type: new Abstract: Mirror randomized benchmarking (MRB) is an established technique that provides a global error metric at the scale of a whole QPU. To expand upon this we introduce Mirror Quantum Awesomeness (MQA), a hybrid protocol that adds a structured entangling layer to MRB circuits. This enables per-edge correlation dynamics to be tracked via mutual information while preserving the MRB infidelity estimate. The resulting analysis of the injected entangled pairs locates a critical circuit depth, beyond which rudimentary error mitigation techniques can be expected to fail. A topological variant, Topological MQA, supplies a second critical depth via a decoder based on the surface-code decoding problem. Both are validated in simulation and demonstrated on the 156-qubit \texttt{ibm\_fez} and \texttt{ibm\_kingston} processors, where MQA closely agrees with MRB on the entanglement infidelity and the critical depth for \texttt{ibm\_fez} is found to be $\sim 50$.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-16

Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement

作者:
Yuhan Chen↗Yicui Shi↗Guofa Li↗Wenxuan Yu↗Ying Fang↗Guangrui Bai↗Wenbo Chu↗Keqiang Li↗

Low-light image enhancement aims to recover clear images from low-illumination observations and is crucial for high-level downstream vision tasks. However, existing methods frequently encounter color distortion and structural artifacts when balancing global smooth illumination adjustment and local high-frequency detail recovery. To address these issues, we propose CGS-Retinex as the first low-light image enhancement framework based on explicit-implicit joint modeling. Our framework deeply integrates continuous Gaussian splatting with Retinex theory. Specifically, we represent the image grid as a continuous parameter field and propose a continuous Gaussian renderer to estimate the spatially continuous global illumination distribution. This approach fundamentally eliminates grid artifacts caused by discrete Gaussian sampling. Furthermore, we introduce an implicit neural representation to model reflectance independently. We leverage shallow high-frequency features to guide the network in accurately reconstructing degraded texture details. Within the Retinex framework, we incorporate physics-inspired brightness consistency constraints and illumination smoothness regularization to enable explicit illumination and implicit reflectance to maintain proper exposure and achieve high-fidelity recovery of high-frequency structures and colors. Extensive experiments demonstrate that CGS-Retinex significantly suppresses dark-region noise and overexposure while achieving exceptional high-frequency structural fidelity and color restoration by precisely decoupling illumination and texture. This work establishes a novel continuous physical representation paradigm for low-light image enhancement.

阅读与讨论 → 访问原文 →