论文广场 - AcademicHub

01.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18721

Rethinking the Pointer Loss in Table Structure Recognition: Geometry-Aware Pointer Loss for Spatial Locality

作者:

Hong-Jun Choi ↗Jongho Lee ↗Jaeyoung Kim ↗

Table Structure Recognition (TSR) using a pointer network achieves impressive results by predicting HTML sequences while aligning tags to detected text (or cell) regions. However, our analysis reveals that when pointer networks fail, 79.6% of errors occur between spatially adjacent cells (Manhattan distance

阅读与讨论 → 访问原文 →

02.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2606.11731

Quantum Correlation Hierarchy and Teleportation in Dephased Hydrogen Hyperfine System

作者:

Geerthana Thiyagarajan ↗R. Muthuganesan ↗

arXiv:2606.11731v1 Announce Type: new Abstract: We study the dynamics of quantum correlations in the hydrogen hyperfine spin system subject to Markovian phase noise. Treating the electron and proton spin degrees of freedom as an open two-qubit system governed by an isotropic hyperfine Hamiltonian and local dephasing, we obtain the exact time-dependent density matrix and derive analytical expressions for the full X-state family. We compute concurrence($C$), trace-distance measurement-induced nonlocality (Trace MIN–$\mathcal{N}_1$), and average steering coherence (ASC) in closed form and establish their strict ordering $ C(t)\leq \mathcal{N}_1(t)\leq \mathrm{ASC}(t) $ at all times. Entanglement is identified as the most fragile resource, undergoing sudden death at a finite time. Trace MIN exhibits dephasing-immune freezing for states with nonzero population imbalance, while ASC is the most robust quantity, persisting longest in every scenario studied.We additionally demonstrate that the dephased thermal hyperfine state serves as a resource for quantum teleportation, deriving a closed-form expression for the average fidelity and establishing that the teleportation advantage window coincides exactly with the entanglement survival interval, $\mathcal{F}_A > 2/3 \Longleftrightarrow \mathcal{C} > 0$, for the full X-state family with maximally mixed marginals. We identify four distinct dynamical regimes and map all three correlation measures onto directly measurable Pauli spin correlators, enabling experimental reconstruction of the full hierarchy without full state tomography.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11256

My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents

作者:

C\'esar Ojeda ↗Darius A. Faroughy ↗Maryam Karimi ↗Payam Zarrintaj ↗Mir Mehdi Seyedebrahimi ↗Mart\'in Carballo-Pacheco ↗

arXiv:2606.11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chemical Harness, a route-native evolutionary framework for goal-directed molecular design in which the search population consists of executable synthetic pathways rather than isolated molecular graphs. Each route is built from purchasable building blocks and reaction templates, executed by deterministic chemistry tools, and scored through task-specific molecular oracles. Large language models (LLMs) are used only as strategy controllers that select high-level preferences over route length, move type, reaction families, motifs, and exploration pressure, while local code performs route construction, validation, deduplication, scoring, selection, and memory updates. This separation lets the LLM guide exploration without allowing it to introduce hallucinated products or unsupported reaction steps. On a soluble epoxide hydrolase proxy task, our LLM agent improves over single pass LLM and deterministic controllers, reaching state-of-the-art performance across the sEH score, synthetic accessibility score, and AiZynthFinder success rate metrics. These results suggest that constrained LLM agents can play a significant role in molecular discovery without requiring training, fine-tuning, or dedicated generative models.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14188

Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation

作者:

Wei-Chen Li ↗Jeffrey Fang ↗Sasanka Polisetti ↗Yuexi Song ↗Glen Chou ↗

arXiv:2606.14188v1 Announce Type: cross Abstract: We present CORD-SLS, a real-time control method for safe deformable object manipulation, with a focus on ropes and cloth. At its core is a GPU-parallel differentiable simulator with contact smoothing which enables efficient gradient-based planning through intermittent contact. To robustly satisfy constraints under model and sensing uncertainty, we develop a real-time, GPU-parallel output-feedback robust model predictive control (MPC) algorithm that plans with this simulator. We further show that the simulator accelerates model-based RL for training neural manipulation policies. To improve real-world robustness, we use conformal prediction to calibrate visual-feedback and perception-error bounds for MPC, producing reachable tubes that enable high-probability safe control. We evaluate CORD-SLS on high-dimensional, contact-rich rope and cloth manipulation tasks in simulation and hardware, including obstacle avoidance, routing, folding, and smoothing. Across settings, CORD-SLS achieves millisecond-speed planning, exceeding baselines in safety, speed, and task success.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2605.31419

Triangle Splatting SLAM

作者:

Nicholas Fry ↗Eric Dexheimer ↗Kirill Mazur ↗Paul H. J. Kelly ↗Andrew J. Davison ↗

We present a dense RGB-D SLAM system using differentiable triangles as the 3D map representation. While 3D Gaussian Splatting has emerged as the leading method for novel-view synthesis, triangles remain the standard primitive for traditional rendering hardware, game engines, and downstream tasks requiring explicit geometry such as simulation, collision, and editing. Recent offline methods have demonstrated that an unstructured 'triangle soup' can be optimised into a photorealistic mesh via Delaunay triangulation across a set of posed images. Building upon this insight, we present the first dense SLAM system to employ Triangle Splatting to perform both tracking and mapping through online differentiable rendering of a triangle soup. The map can be converted into a connected mesh on-the-fly via restricted Delaunay triangulation, enabling new online capabilities such as mesh deformation and collision checking. On Replica and TUM-RGBD, our system outperforms baselines on 3D geometry, matches the camera-tracking accuracy, and enables online mesh-based scene editing.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16190

Embedded Arena: Iterative Optimization via Hardware Feedback

作者:

arXiv:2606.16190v1 Announce Type: cross Abstract: Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints. Optimizing models for heterogeneous microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware – compiling, flashing, and measuring on real hardware – to enable closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2604.13082

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

作者:

Laura Gomezjurado Gonzalez ↗

arXiv:2604.13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood. In encoder-decoder arithmetic models, we argue that this delay reflects limited access to already learned structure rather than failure to acquire that structure in the first place. We study one-step Collatz prediction and find that the encoder organizes parity and residue structure within the first few thousand training steps, while output accuracy remains near chance for tens of thousands more. Causal interventions support the decoder bottleneck hypothesis. Transplanting a trained encoder into a fresh model accelerates grokking by 2.75 times, while transplanting a trained decoder actively hurts. Freezing a converged encoder and retraining only the decoder eliminates the plateau entirely and yields 97.6% accuracy, compared to 86.1% for joint training. What makes the decoder's job harder or easier depends on numeral representation. Across 15 bases, those whose factorization aligns with the Collatz map's arithmetic (e.g., base 24) reach 99.8% accuracy, while binary fails completely because its representations collapse and never recover. The choice of base acts as an inductive bias that controls how much local digit structure the decoder can exploit, producing large differences in learnability from the same underlying task.

阅读与讨论 → 访问原文 →

08.

medRxiv (Medicine) 2026-06-22 DOI: HASH:ae80a10ef68fe15ecfc78f7e1196c01c

Building accessible resources to empower communities: the case of the Lupus Mexican Registry

作者:

Martinez ↗Sanchez-Aguirre ↗Sevilla-Parra ↗Olivares-Martinez ↗Bravo-Garcia ↗Hernandez-Ledesma ↗A. L ↗Aguilar ↗L. A ↗Dominguez-Frausto ↗C. A ↗Garcia ↗…

Motivation: Although SLE data in Latin America is increasing, clinical datasets remain difficult to access and interpret, highlighting the need for accessible tools that support data-driven precision medicine, citizen science, and public health initiatives. Results: We developed a user-friendly platform that enables us to explore LupusRGMX data through interactive queries, report generation, statistical modeling, and comprehensive insights. This resource supports community-oriented research, improves the visibility of underrepresented populations in lupus research, and provides a useful tool to enhance data accessibility. Availability and implementation: Developed in R using Shiny and bslib for interactive visualization and interface design. Available at https://github.com/NeuroGenomicsMX/Lupus_App_2.0 and https://lupusrgmx.liigh.unam.mx/shiny/lupus/

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2604.20236

Machine Learning-based Two-Stage Graph Sparsification for the Travelling Salesman Problem

作者:

Bo-Cheng Lin ↗Yi Mei ↗Mengjie Zhang ↗

arXiv:2604.20236v2 Announce Type: replace Abstract: High-performance TSP solvers such as Lin-Kernighan-Helsgaun (LKH) search within a candidate graph – a small subset of edges pre-selected for the solver – rather than over the complete graph. The two leading sparsification heuristics, $\alpha$-Nearest and POPMUSIC, each fall short of the density-coverage balance: $\alpha$-Nearest is dense with stable recall, while POPMUSIC is sparser but its recall degrades with scale. Their union closes the recall gap while remaining far below the complete graph in density, leaving room for further reduction. Existing learning-based sparsifiers score edges on the complete graph, an approach that is expensive and largely limited to Euclidean instances. We propose a two-stage method that inverts this logic. Stage~1 takes the union of $\alpha$-Nearest and POPMUSIC, achieving near-perfect recall at ${\sim}6N$ edges. Crucially, the union annotates each edge with its source provenance – whether it was endorsed by $\alpha$-Nearest, POPMUSIC, or both. Stage~2 trains a lightweight classifier on these annotated edges and prunes the lowest-scoring ones. Because dual-source edges are almost always optimal, the learning problem reduces to filtering the single-source subset – a substantially easier task than classifying all $O(N^2)$ edges from scratch. Across four distance types, five spatial distributions, and problem sizes from 50 to 500, the pipeline reduces candidate-graph density by $37$-$47\%$ while retaining ${\geq}99.69\%$ of optimal-tour edges, and matches or exceeds the coverage of recent Euclidean-only neural sparsifiers at lower density at TSP500.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17688

LLMs Infer Cultural Context but Fail to Apply It When Responding

作者:

Yisong Miao ↗Jian Zhu ↗Vered Shwartz ↗

Recent work has shown that LLMs overrepresent dominant cultures, particularly Western ones, while marginalizing others. We investigate whether this affects models' ability to generate culturally adapted responses by evaluating their use of local measurement units based on the user's perceived cultural background. We introduce Cultural and Pragmatic Response Inference (CAPRI), a dataset of conversations with varying levels of cultural cues. Experiments with state-of-the-art LLMs show that models can infer cultural background and recall relevant conventions, but often fail to utilize the information to adapt their answers to the relevant cultural conventions, unless explicitly prompted to perform the tasks sequentially. We further evaluate adaptation to the interpretation of time and quantity expressions, two subjective language grounding dimensions that are affected by culture. We find that models increasingly adapt their answers as cultural cues accumulate, but their priors are not culture-neutral, sometimes aligning with the model's country of origin. Overall, CAPRI provides a resource for future research aimed at narrowing the gap between cultural knowledge and culturally adaptive language generation.

阅读与讨论 → 访问原文 →

11.

PLOS Computational Biology 2026-06-01 DOI: HASH:432e24ef8ff14eeab8a22ee9591a7155

Challenges and progress in RNA velocity: Comparative analysis across multiple biological contexts

作者:

Sarah Ancheta ↗

by Sarah Ancheta, Leah Dorman, Guillaume Le Treut, Abel Gurung, Greg Huber, Loïc A. Royer, Alejandro Granados, Merlin Lange Single-cell RNA sequencing is revolutionizing our understanding of cell state dynamics, allowing researchers to capture and quantify the transcriptomic profile of a single cell at a specific timepoint. Among the computational techniques used to predict cellular trajectories, RNA velocity has emerged as a predominant tool for modeling transcriptional dynamics. RNA velocity leverages the mRNA maturation process to generate velocity vectors that predict the likely future state of a cell, offering insights into cellular differentiation, aging, and disease progression. Although this technique has shown promise across biological fields, the performance accuracy varies depending on the RNA velocity method and dataset. We established a comparative pipeline and analyzed the performance of five RNA velocity methods on three datasets based on local consistency, method agreement, identification of driver genes, and robustness to sequencing depth. This benchmark provides a resource for scientists to understand the strengths and limitations of different RNA velocity methods.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20223

DeepForestVisionV2: Ecology-Driven Taxonomy Expansion for Camera-Trap Monitoring in African Tropical Forests

作者:

Camera-trap monitoring in African tropical forests increasingly extends beyond closed-canopy interiors to riverbanks, clearings, and park edges. Among available open tools for African forest camera-trap classification, DeepForestVision is the only one providing a matched offline workflow for both photographs and videos, and previous work showed that it outperformed other available baselines on a comparable benchmark. However, it was designed for closed-canopy, ground-level forest interiors and uses a 35-class prediction space that becomes too coarse when deployments encounter arboreal primates, birds, semi-aquatic taxa, or human-associated confounders such as livestock. We present DeepForestVisionV2, an ecology-driven expansion from 35 to 64 prediction classes (61 animal classes plus human, vehicle, and blank) designed to address three recurrent deployment gradients: vertical stratification, scene openness, and anthropogenic interfaces. DeepForestVisionV2 retains the same offline workflow and is trained on 1,535,010 photographs and 243,354 videos from multi-country African tropical-forest projects. Evaluation combines a cross-country cropped-photo validation set, used to assess robustness across sites and camera-trap settings, with three held-out Uganda video benchmarks spanning the targeted gradients. On the validation set, DeepForestVisionV2 reaches 0.86 accuracy, 0.82 macro-F1, and 0.81 balanced accuracy. On the deployment benchmarks, it preserves or improves baseline accuracy despite its harder classification task, while increasing the number of identified taxa from 22 to 29 in forest-interior videos and from 4 to 9 at riverbanks. In the park-edge use case, it raises accuracy from 0.62 to 0.86 and reduces false alarms from 11 to 0. These results show that DeepForestVisionV2 materially improves field utility while preserving robustness across sites, habitats, and camera-trap settings.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2602.11557

The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient

作者:

Jichu Li ↗Xuan Tang ↗Difan Zou ↗

arXiv:2602.11557v2 Announce Type: replace Abstract: A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest descent in multi-class classification, characterizing how batch size, momentum, and variance reduction shape the limiting max-margin behavior and convergence rates under general entry-wise and Schatten-$p$ norms. We show that, without momentum, worst-case convergence and successful classification can only be guaranteed with full-batch gradient. In contrast, momentum enables small-batch convergence to an approximate max-margin solution through a batch-momentum trade-off, though it slows convergence. This approach provides fully explicit, dimension-free rates that improve upon prior results. Moreover, we prove that variance reduction can recover the exact full-batch implicit bias for any batch size, albeit at a slower convergence rate. Finally, we further investigate the batch-size-one steepest descent without momentum, and reveal its convergence to a fundamentally different bias via a concrete data example, which reveals a key limitation of purely stochastic updates. Overall, our unified analysis clarifies when stochastic optimization aligns with full-batch behavior, and paves the way for perform deeper explorations of the training behavior of stochastic gradient steepest descent algorithms.

阅读与讨论 → 访问原文 →

14.

Nature (Science) 2026-06-10 DOI: HASH:0ab59bdf15d606bd524337deb0a7a95d

When drug discovery fails: scientists share their frustrations with the process

作者:

Tammy Worth ↗

In clinical trials, there are many times (and ways) a therapeutic can come up short. In clinical trials, there are many times (and ways) a therapeutic can come up short.

阅读与讨论 → 访问原文 →

15.

Science (Express) 2026-06-18 DOI: 10.1126/science.aef5355

Indium-free perovskite/silicon tandem solar cells with tin oxide recombination layer and electrodes | Science

作者: 未知作者

Indium-based transparent conductive oxides are widely used as electrodes and recombination layers in perovskite/silicon tandem solar cells, yet their scalability is constrained by indium scarcity and sputtering-induced damage. Here we report high efficiency and stable indium-free perovskite/silicon tandem solar cells enabled by reactive plasma deposited tin oxide (RPD-SnO x ). For RPD-SnO x as the recombination layer, a certified efficiency of 33.6% is achieved. Fully indium-free tandems that used RPD-SnO x as both recombination layer and electrodes delivering a champion PCE of 33.2% (1 cm 2 ) and a mini-module with a certified efficiency of 31.0% (207.9 cm 2 ). Dense and uniform self-assembled monolayer anchoring enabled by RPD-SnO x suppressed non-radiative recombination and reduced halide migration. Indium-free mini-modules exhibited high thermal, damp-heat, and outdoor operational stability and retained 65% of their maximum initial efficiency after 105 days of outdoor operation.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20058

Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale

作者:

Harsh Rao Dhanyamraju ↗Leonidas Raghav ↗Aaron Lee ↗

arXiv:2606.20058v1 Announce Type: new Abstract: Enterprise AI aims to move toward continuous event monitoring, detection, and action across specialist agents, yet existing multi-agent systems largely assume discrete request-response workflows and remain underexplored at enterprise scale. We evaluate DAG Plan and Execute and ReAct across 208 production-derived enterprise scenarios spanning Persona (

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18893

Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction

作者:

Zhuangzhuang Pan ↗Ning Dong ↗Yingna Su ↗Yan Xia ↗

Multimodal emotion-cause pair extraction (MECPE) requires reliable pair confidence over candidate pairs. Existing pair scorers commonly use pair-level cross entropy over valid candidates, which treats links mostly independently. This leaves the relative confidence geometry among competing causes under-constrained, allowing gold pairs to stay close to hard negatives or rely on incidental non-gold context. We study this vulnerability as pair-confidence brittleness and propose RPCL (Robust Pair Confidence Learning), a training-only framework for pair-confidence learning. RPCL encourages pair confidence to be both discriminative and stable: gold pairs are separated from row-wise hard negatives through a confidence-difference margin constraint, and clean pair predictions are aligned with predictions from a corrupted view where non-gold contextual utterance representations are partially corrupted. The original clean pair scorer and decoding pipeline are used unchanged at inference time. On ECF, MECAD, and MEC4, RPCL improves the three-seed mean Pair F1 over a matched base model by 2.58 to 2.83 percentage points in the full text-audio-video setting, and improves mean Pair AUPRC on all three datasets. Diagnostic analysis further shows larger gold-negative confidence gaps and lower margin-violation severity. These results suggest that explicitly shaping pair confidence is an effective training strategy for MECPE.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12913

Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration

作者:

Dongyue Wu ↗Zilin Guo ↗Xiaoyu Li ↗Jiajia Liu ↗Jingdong Chen ↗Nong Sang ↗Changxin Gao ↗

The rapid growth of modern training datasets has significantly increased computational cost, motivating dataset pruning~(DP) methods which retain only a subset of informative samples to reduce training cost. Existing pruning criteria typically rely on either intrinsic signals that assess samples independently or extrinsic signals that promote diversity via pairwise relations. While effective in their own specific regimes, each captures only one aspect of sample utility and lacks robustness across different pruning ratios or data distribution. In this work, we present a unified graph-based DP framework. By modeling the dataset as a weighted graph, where node weights encode intrinsic value and edge weights encode extrinsic value, DP can be cast as a Maximum Weight Clique Problem (MWCP). Although MWCP is NP-hard, its structure admits a principled greedy solution based on sample-wise marginal gains. Under a few mild conditions, we further prove that this unified objective enjoys a formal approximation guarantee, which applies to a broad family of importance metrics and provides practical design guidelines. Extensive experiments show that our method outperforms existing DP methods while substantially reducing training cost, reducing training time by over 40\% without sacrificing accuracy on ImageNet-1k with ResNet-50.

阅读与讨论 → 访问原文 →

19.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.19457

Efficient classical representation and quantum state preparation of complete active space wavefunctions

作者:

Hamza Jnane ↗

arXiv:2606.19457v1 Announce Type: new Abstract: Quantum computers promise to solve the electronic structure problem for a large class of molecules. However, the performance of relevant quantum algorithms hinges on preparing initial states with substantial overlap with the target eigenvector. For classically challenging molecules with strong electron correlation, starting from multi-reference states, such as complete active space (CAS) wavefunctions is necessary. Unfortunately, the most advanced state preparation protocols applied to such states result in a gate complexity that scales exponentially with the active space size $d$. In fact, even encoding a CAS state classically is traditionally believed to be intractable for chemically relevant systems. Here, we draw insights from the recently introduced Quantum Paldus Transform (QPT) to show that there exists an efficient classical representation of CAS states and to design a new state preparation routine outperforming previous ones. The QPT represents a transformation from the Fock basis to a friendlier symmetry-adapted basis. Our main contribution consists in showing that CAS states expanded in this basis can efficiently be represented as a matrix product state (MPS) with a bond dimension scaling as $O(d^2)$. One can then efficiently load the MPS on a quantum computer and use the inverse QPT to transform the state to the Fock basis. Moreover, our method can easily be extended to the efficient preparation of CAS states in first quantisation with similar complexity. Crucially, we demonstrate that the complexity of both state preparation protocols only grows polynomially as $O(d^3)$ , which constitutes to the best of our knowledge an exponential improvement over the state of the art.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2510.01444

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning

作者:

Rui Liu ↗Dian Yu ↗Tong Zheng ↗Runpeng Dai ↗Zongxia Li ↗Wenhao Yu ↗Zhenwen Liang ↗Linfeng Song ↗Haitao Mi ↗Pratap Tokekar ↗Dong Yu ↗

Reinforcement learning with verifiable rewards (RLVR) has advanced reasoning capabilities in multimodal large language models. However, existing methods typically treat visual inputs as deterministic, overlooking the perceptual ambiguity inherent to the visual modality. Consequently, they fail to distinguish whether a model's uncertainty stems from complex reasoning or ambiguous perception, preventing the targeted allocation of exploration or learning signals. To address this gap, we introduce DUPL, a dual-uncertainty guided policy learning approach for multimodal RLVR that quantifies and leverages both perceptual uncertainty (via symmetric KL divergence) and output uncertainty (via policy entropy) to guide policy updates. By establishing an uncertainty-driven feedback loop and employing a dynamic branch prioritization mechanism, DUPL recalibrates the policy advantage to focus learning on states with high perceptual or decisional ambiguity, enabling effective targeted exploration beyond passive data augmentation. Evaluated on diverse multimodal reasoning benchmarks spanning mathematical and general domains, DUPL achieves solid gains. It improves Qwen2.5-VL accuracy by up to $12.3%$ (3B) and $7.9%$ (7B), and Qwen3-VL-Instruct by up to $10.7%$ (4B) and $12.4%$ (8B), consistently outperforming GRPO, while seamlessly generalizing to alternative algorithms (DAPO, $+6.5%$ avg) and architectures (LLaVA-OneVision-1.5, $+4.7%$ avg). These results demonstrate that DUPL is an effective and generalizable approach for multimodal RLVR.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16456

SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling

作者:

Weiqiao Shan ↗Ruixiang Mao ↗Yuang Li ↗Yuhao Zhang ↗Yingfeng Luo ↗Tong Zheng ↗Chen Xu ↗Yucheng Qiao ↗Chunxiang Jin ↗Yi Yuan ↗Jingdong Chen ↗Tong Xiao ↗…

arXiv:2606.16456v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained dense models into sparse MoE models. However, existing upcycling methods typically rely on large-scale continued training and often perform poorly under data-constrained supervised adaptation, due to either homogeneous experts or overly disruptive perturbations to pretrained parameters. In this setting, effective upcycling must leverage pretrained weight structure while introducing sufficient diversity among routed experts. To this end, we propose SVD-Partitioned Residual Initialization (SPRI), which distributes SVD-partitioned residuals derived from pretrained feed-forward network (FFN) weights across routed experts, introducing controlled expert diversity grounded in pretrained spectral structure. We further introduce a two-stage training strategy to improve adaptation stability. We evaluate SPRI on multilingual speech-to-text translation, where limited supervised data challenges MoE upcycling and multiple target languages provide natural routing heterogeneity. On CoVoST2 across 15 En-to-XX directions, SPRI improves average BLEU and COMET over fully fine-tuned dense models by 2.58 and 3.32 points, respectively, and outperforms the prior best MoE upcycling baseline by 3.39 BLEU and 4.34 COMET points.

阅读与讨论 → 访问原文 →

22.

Nature (Science) 2026-06-10 DOI: HASH:e89f9a3fde51fe3ac81b3caf501e7fae

Gene ancestries reveal diverse microbial associations during eukaryogenesis

作者:

Moisès Bernabeu ↗

The origin of eukaryotes remains a central enigma in biology1. Continuing debates agree on the pivotal role of a symbiosis between an alphaproteobacterium and an Asgard archaeon2,3. However, the nature, timing and contributions of other potential bacterial partners4–6 and the role of interactions with viruses7–9 remain contentious. To address these questions, we used advanced phylogenomic approaches and comprehensive datasets spanning the known diversity of cellular life and viruses. Our analysis provided a revised reconstruction of the last eukaryotic common ancestor (LECA) proteome, in which we traced the phylogenetic origin of each protein family. We found compelling evidence for multiple waves of horizontal gene transfer from diverse bacterial donors, with some likely to have preceded mitochondrial endosymbiosis. We inferred plausible traits of the major donors and their functional contributions to the LECA. Our findings support a contribution of horizontal gene transfers to shaping the proteomes of pre-LECA ancestors and suggest a facilitating role of Nucleocytoviricota viruses. Taken together, our results suggest that ancient eukaryotes may have originated within complex microbial ecosystems through a succession of diverse associations that left a footprint of horizontally transferred genes. Phylogenomic reconstruction of the proteome of the last eukaryotic common ancestor sheds light on the origin of eukaryotes, indicating an important role of horizontal transfer of genes from diverse bacterial and viral donors.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2602.00845

Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward

作者:

Senkang Hu ↗Yong Dai ↗Yuzhi Zhao ↗Yihang Tao ↗Yu Guo ↗Zhengru Fang ↗Sam Tak Wu Kwong ↗Yuguang Fang ↗

arXiv:2602.00845v3 Announce Type: replace Abstract: Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, but yet optimizing the retrieval process remains challenging due to the lack of dense, principled reward signals. In this paper, we introduce InfoReasoner, a unified framework that incentivizes effective information seeking via a synthetic semantic information gain reward. Theoretically, we redefine information gain as uncertainty reduction over the model's belief states, establishing guarantees, including non-negativity, telescoping additivity, and channel monotonicity. Practically, to enable scalable optimization without manual retrieval annotations, we propose an output-aware intrinsic estimator that computes information gain directly from the model's output distributions using semantic clustering via bidirectional textual entailment. This intrinsic reward guides the policy to maximize epistemic progress, enabling efficient training via Group Relative Policy Optimization (GRPO). Experiments across seven question-answering benchmarks demonstrate that InfoReasoner consistently outperforms strong retrieval-augmented baselines, achieving up to 5.4% average accuracy improvement. Our work provides a theoretically grounded and scalable path toward agentic reasoning with retrieval. The code is available at https://github.com/dl-m9/InfoReasoner

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14693

Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning

作者:

Pengxin Wang ↗Lihao Guo ↗Yi Xie ↗Bo Liu ↗Siyang Cao ↗Jingdi Chen ↗

arXiv:2606.14693v1 Announce Type: cross Abstract: Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19627

VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions

作者:

arXiv:2606.19627v1 Announce Type: cross Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds. This transition introduces an ``extreme cold-start'' problem: unlike traditional items, new short-form videos lack the dense interaction history required for collaborative filtering. Furthermore, immersive feeds introduce strong position and duration biases that distort standard engagement signals. In this paper, we demonstrate the Video Candidate Generation (VCG) system, a scalable multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment. By leveraging a domain-adapted vision-language model (based on CLIP), we map users and videos into a shared semantic space, enabling zero-shot retrieval based on visual content rather than behavioral history. We detail the system's architecture and present a rigorous evaluation comparing generative (LLM) vs. discriminative (CLIP) embeddings. Our results show that while generative models excel at attribute prediction, they suffer from embedding space collapse in retrieval tasks. Online A/B testing demonstrates that VCG effectively mitigates engagement biases, yielding a 50\% uplift in deep video completion. To showcase the system's capabilities, we present an interactive demonstration featuring three bi-directional retrieval scenarios: Product-to-Video, Video-to-Product, and Zero-Shot Semantic Search.

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络