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
作者: Teng ×
↻ 换一批
01.
arXiv (CS.CV) 2026-06-11

Findings of the MAGMaR 2026 Shared Task

作者:
Alexander Martin↗Dengjia Zhang↗Joel Brogan↗Francis Ferraro↗Jeremy Gwinnup↗Reno Kriz↗Teng Long↗Kenton Murray↗Andrew Yates↗Xiang Xiang↗

This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR). In this shared task participants submitted systems focused on either (i) video retrieval or (ii) grounded generation of articles given retrieved videos. Teams could submit to either task. For the retrieval task, we had 2 participating teams that submitted a total of 17 systems – all of which beat a baseline derived from the winner of last year's shared task. On the generation side, we had 4 teams submit 16 systems. All teams had at least one generated report that was labeled the best by a human annotator.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.LG) 2026-06-16

Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization

作者:
Kaiyue Wen↗Xingyu Dang↗Kaifeng Lyu↗Tengyu Ma↗Percy Liang↗

arXiv:2606.16899v1 Announce Type: new Abstract: Matrix based optimizers such as Muon can substantially speed up language model pretraining, but their gains over AdamW are observed to shrink as model size and data scale grow when using standard constant decoupled weight decay. We propose Hyperball, a simple optimizer wrapper that addresses this issue. Given a base optimizer such as Adam or Muon, Hyperball sets the Frobenius norms of weight matrices and their corresponding optimizer updates to fixed constants. On Qwen3 style models up to 1.2B parameters, Muon Hyperball achieves 20–30% token equivalent speedup over weight decay baselines. Hyperball also improves learning rate transfer across widths and depths compared to decoupled weight decay. This method is motivated by prior theory showing that training with weight decay leads to an equilibrium weight norm that only depends on the training hyperparameters. Through this mechanism, the weight decay then decides the angular learning rate, i.e. how fast the direction of the weight matrix changes.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-18

CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents

作者:
Jiaqi Chen↗Yongqin Zeng↗Shaoshen Chen↗Yijian Zhang↗Hai-Tao Zheng↗Chunxia Ma↗XiuTeng Zhou↗

Personalized dialogue agents require continuous long-term memory to maintain coherent interactions across multiple sessions. However, deploying these capabilities on consumer-grade hardware (e.g., 8 GB VRAM edge devices) introduces severe memory and compute bottlenecks. Existing systems typically rely on isotropic cosine similarity for retrieval and heuristic rules for context compression. These approaches lack a unified theoretical foundation, frequently suffering from the hubness problem in high-dimensional retrieval and syntactic fragmentation during compression. To overcome these limitations, we propose CoreMem, a resource-efficient edge-cloud memory architecture fundamentally unified by information geometry. First, Riemannian retrieval replaces cosine matching with a locally adaptive Fisher-Rao metric, effectively penalizing hub memories via Mahalanobis distance with O(Ndr) Woodbury acceleration for real-time search. Second, Fisher-guided discrete token distillation (FDTD) introduces a hierarchical sentence-to-token compression mechanism. It derives sensitivity scores from Fisher information traces, providing a principled compression-KL tradeoff augmented with explicit structural syntax protection. Evaluated on the LOCOMO and LongMemEval-S benchmarks, CoreMem achieves strong accuracy improvements, yielding substantial gains in Open-domain (+4.51 pp) and Temporal (+4.17 pp) reasoning. Extensive profiling confirms that CoreMem operates seamlessly within a strict 8 GB VRAM budget, successfully bridging the gap between resource-constrained edge devices and the demand for theoretically grounded, lifelong memory agents.

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

Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach

作者:
Ruichao Mao↗Zhou Fang↗Teng Guo↗Hao Yang↗Yaping Li↗Shaohua Peng↗Maji Huang↗Xiaoyu Lin↗Shuoyang Liu↗Xuepeng Li↗Yuyu Zhang↗Hai Rao↗…

arXiv:2606.13192v1 Announce Type: new Abstract: User experience (UX) centered on usability, perceived consistency, and functional clarity is fundamental to real-world user interfaces (UI). The application of multimodal large language models (MLLMs) in the field of user interfaces is evolving rapidly, such as visual element grounding, graphical user interface (GUI) agents, and design-to-code generation. However, research efforts on evaluating UX based on UI screenshots are still immature. To address this, we propose UXBench, a novel multimodal benchmark consisting of 2,000 VQA data samples designed to assess MLLMs' ability to perform UI-based reasoning. UXBench includes 8 tasks based on real-world UI screenshots that require fine-grained diagnosis of UX issues across layout relationships, visual hierarchy, and content consistency. Our extensive evaluation of mainstream MLLMs shows that they remain fundamentally limited in their capacity for UI-based reasoning. The results underscore the need for further advancements in this area. To bridge this gap, we propose UI-UX, an MLLM based on Qwen3-VL-4B-Thinking foundation model and enhanced via reinforcement learning with two key innovations: a reward routing mechanism that dynamically balances perceptual understanding and logical reasoning during inference, and an asymmetric transition reward that suppresses redundant or insufficient reasoning steps. Experiments demonstrate that UI-UX achieves state-of-the-art (SOTA) performance on UXBench, attaining an accuracy of 0.7963 – surpassing Claude-4.5-Sonnet's 0.6550 – while exhibiting strong generalization across diverse UI tasks and maintaining low inference latency.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.CV) 2026-06-16

Propagating Structural Guidance: Synthesizing Fluorescein Angiography from Fundus Images and Sparse OCT Scans

作者:
Tengfei Ma↗Ruiqi Wu↗Chenran Zhang↗Ye Geng↗Na Su↗Xiangyuan Duanmu↗Tao Zhou↗Yi Zhou↗Wen Fan↗

Fundus fluorescein angiography (FFA) is critical for assessing retinal vascular abnormalities, but its acquisition is invasive and not always feasible. In contrast, color fundus photography (CFP) is non-invasive and widely accessible, which has motivated studies on CFP-to-FFA synthesis. However, prior works rely solely on CFP surface texture, fundamentally limiting the ability to reconstruct functional vascular information and subtle pathological changes. To address this, we propose a novel framework that synthesizes FFA from CFP with structural guidance provided by optical coherence tomography (OCT). We construct a multi-modal retinal imaging dataset with paired CFP, FFA, and OCT from 3,676 patient eyes–the first tri-modally aligned dataset in retinal imaging. To bridge the spatial gap between OCT and fundus modalities, we propose a Spatially Aligned Cross-Modal Fusion (SACMF) module that projects depth-resolved OCT features onto the fundus plane and injects them into the CFP encoder via adaptive layer normalization. Beyond feature fusion, we further introduce Token-wise Cross-Modality Alignment (TCMA), a token-level contrastive learning strategy that explicitly aligns CFP and FFA representations at corresponding spatial positions. Our method achieves superior synthesis performance compared to state-of-the-art methods. Moreover, extensive experiments demonstrate that the FFA images synthesized by our approach bring greater improvements in downstream disease diagnosis performance than existing methods, highlighting the clinical potential of our approach as a non-invasive decision-support tool in routine workflows. The code is available at https://github.com/while-plus/OCT-guide-FFA-Syn.

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

MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model

作者:
Lichen Bai↗Tianhao Zhang↗Shitong Shao↗Dingwei Tan↗Qiyu Zhong↗Zhengpeng Xie↗Haopeng Li↗Qinghao Huang↗Dandan Shen↗Tengjiao Ji↗Wei Wang↗Peicheng Wu↗…

As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototype model as the first step towards this goal. While previous world models successfully simulate physical environments or gaming world exploration, they remain fundamentally detached from human-centric social dynamics. To bridge this gap as the first step to social world models, we present MaineCoon, the first real-time audio-visual autoregressive model that has 22B parameters and is capable of real-time streaming generation and sub-second interaction, with a record-breaking frame rate of up to 47.5 FPS, on a single GPU. To the best of our knowledge, MaineCoon is also the first real-time audio-visual generation model specifically optimized for social-interactive applications. To enable efficient and stable training, we introduce several novel techniques into MaineCoon, including self-resampling, cross-modal representation alignment, domain-aware preference optimization, and reinforced online-policy distillation (ROPD). We also design the first agentic streaming inference framework that supports thousand-second-scale or even longer generation while mitigating drift with agentic cache management and prompt planing. These innovations significantly accelerate training while optimizing real-time inference performance. We believe this work not only sets a new state-of-the-art (SOTA) performance benchmark for high-quality, low-latency, and long-horizon audio-visual autoregressive models, but also points out the paradigm shift desired for next-generation AI-native social platforms.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CL) 2026-06-16

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

作者:
Luo Ji↗Qi Qin↗Ningyuan Xi↗Teng Chen↗Qingqing Gu↗Hongyan Li↗

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $\beta$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $\beta$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CL) 2026-06-17

PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience

作者:
Xinyang Liao↗Lingyu Li↗Huacan Liu↗Tianle Gu↗Yang Yao↗Tong Zhu↗Yan Teng↗Yingchun Wang↗

As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Otherwise, such systems may rapidly generate plausible yet misleading studies that contaminate academic literature and erode trust in science. We present PseudoBench, an adversarial benchmark for evaluating whether agentic auto-research systems can identify and resist pseudoscientific narratives. PseudoBench contains 200 curated pseudoscientific claim-evidence pairs across five domains and evaluates agents through an end-to-end research pipeline from experiments to writing. Testing seven state-of-the-art agents, we find that current systems readily produce persuasive reports that align with pseudoscientific premises with near-zero refusal rates and the highest resistance of only 27.4%. Stronger agents risk packaging pseudoscience in more sophisticated scientific language, increasing its apparent credibility. These findings reveal an alarming capacity to fuel pseudoscience, calling for scientific alignment before widespread deployment.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CL) 2026-06-17

EmoFSM: A Finite State Machine for Emotional Support Conversation

作者:
Yue Zhao↗Qingqing Gu↗Xiaoyu Wang↗Teng Chen↗Zhonglin Jiang↗Yong Chen↗Hongyan Li↗Luo Ji↗

Emotional support conversation (ESC) aims to alleviate people's emotional distress through effective conversations. Although large language models (LLMs) have made remarkable progress in ESC, most of these studies may not define the diagram from a state-model perspective, thereby providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Finite State Machine (FSM) on LLMs, and propose a framework called EmoFSM. Our framework allows a single LLM to bootstrap the planning during ESC, and self-reason the seeker's emotion, support strategy, and the final response upon each conversation turn. Substantial experiments in ESC datasets suggest that EmoFSM outperforms many baselines, including direct inference, self-fine, chain of thought, finetuning, and externally supported methods, even those with many more parameters.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.AI) 2026-06-15

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

作者:
Tingyang Chen↗Shuo Lu↗Kang Zhao↗Weicheng Meng↗Hanlin Teng↗Tianhao Li↗Chao Li↗Xule Liu↗Jian Liang↗Zhizhong Zhang↗Yuan Xie↗Heng Qu↗…

arXiv:2606.14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

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

SoftSkill: Behavioral Compression for Contextual Adaptation

作者:
Xijia Tao↗Yihua Teng↗Xinyu Fu↗Ziru Liu↗Kecheng Chen↗Yuzhi Zhao↗Suiyun Zhang↗Rui Liu↗Lingpeng Kong↗

arXiv:2606.20333v1 Announce Type: new Abstract: Agent skills are commonly deployed as natural-language Markdown files that encode answer policies, evidence-use habits, and task procedures. These files are readable and portable, but they are consumed indirectly: for each task instance, a frozen language model must translate a long textual artifact into generation-time behavior. This paper asks whether a natural-language skill can instead initialize a compact continuous context object, refined by a trainable soft delta while the base model remains frozen. We propose SoftSkill, a frozen-backbone method that tunes such soft skills with next-token prediction and deploys them as latent behavioral priors at inference time. In our main single-round setting, a length-32 SoftSkill prefix on Qwen3.5-4B improves over no-skill prompting by 8.3 points on SearchQA, 42.1 points on LiveMath, and 1.3 points on DocVQA. Relative to SkillOpt, SoftSkill improves accuracy by 5.2 points on SearchQA and 12.5 points on LiveMath, while replacing hundreds to thousands of Markdown skill tokens with a few virtual tokens. We further study agentic execution as a harder boundary case, where sparse trajectory imitation provides useful signal but does not yet robustly compress long-horizon procedural behavior. More broadly, the results suggest that some task skills are better treated not as additional Markdown to be reinterpreted at inference time, but as compact latent controls over how a frozen model enters the task.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.LG) 2026-06-18

Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS

作者:
Siyuan Dai↗Yang Du↗Kun Zhao↗Zhusuyi Chen↗Heng Huang↗Paul Thompson↗Chao Shi↗Haoteng Tang↗Liang Zhan↗

arXiv:2606.18287v1 Announce Type: new Abstract: Multimodal neuroimaging, integrating functional connectivity from fMRI and structural connectivity from DTI, enables non-invasive analysis of brain networks using graph neural networks. However, demographic factors such as age and sex systematically confound the relationship between brain connectivity and clinical outcomes, causing GNNs to exploit spurious shortcuts rather than learning causally invariant representations. While recent causal GNN methods introduce causality at the graph-modeling level, their causal mechanisms remain domain-agnostic without accounting for the real-world confounders inherent in clinical neuroimaging data. Moreover, brain networks are constructed from atlas-based parcellations where each region exhibits distinct sensitivity to demographic factors, necessitating region-aware adjustment. We propose Artemis, a region-level causal framework that bridges this gap with causal intervention at each brain region independently by learning region-specific confounder representations with lightweight parameters. Our adjustment comprehensively utilized the multimodal functional and structural features for graph reasoning as a plug-in module compatible with arbitrary GNN backbones. Experiments on three benchmarks, ADNI for disease diagnosis, OASIS for dementia staging, and HCP for sex classification, demonstrate consistent improvements over representative GNN-based baselines. Multiple supporting experiments further demonstrate statistical significance and neuroscientific interpretability.

阅读与讨论 → 访问原文 →
13.
arXiv (quant-ph) 2026-06-12

Stable, bidirectional electro-optic transduction in thin film lithium tantalate

作者:
Christopher J. Axline↗Stephan Gamper↗Phoebe M. Tengdin↗Moritz Businger↗Guilhem Alma↗Marina A. Roquet↗Nicola Brusadin↗Robin Giroud↗Luis G. Villanueva↗

arXiv:2606.12726v1 Announce Type: new Abstract: Efficient and stable microwave-optical transduction is a key enabling technology for distributed superconducting quantum computing and heterogeneous quantum networks. Electro-optic transducers based on thin-film lithium niobate (TFLN) have shown strong promise, but demonstrations to date have been limited by various factors such as low frequency bias drift, low efficiency, fabrication complexity, and scalability. Here we demonstrate the first integrated electro-optic microwave-optical transducers realized in thin-film lithium tantalate (TFLT), a material platform offering Pockels nonlinearity comparable to TFLN together with improved bias stability and high-power handling. We fabricate superconducting microwave resonators coupled to tunable photonic-molecule optical resonators using wafer-scale deep ultraviolet lithography, offering high-throughput production of hundreds of devices per wafer. Across six devices we observe coherent bidirectional conversion between C-band optical photons and 4.9-5.5 GHz microwave photons, with measured on-chip efficiencies and inferred single-photon coupling rates g_0/2{\pi} ~ 1 kHz consistent with theory. Continuous operation over multiple days is achieved using a static bias field with minimal feedback, demonstrating a major operational advantage. We further characterize optical loss statistics, microwave resonator performance, and optically induced added noise under pulsed pumping, finding less than one added photon for 100 microsecond pulses at the highest measured efficiencies. These results establish TFLT as a scalable and robust electro-optic platform for future quantum interconnects and modular quantum processors.

阅读与讨论 → 访问原文 →
14.
arXiv (math.PR) 2026-06-16

Risk-averse mean field games: exploitability and non-asymptotic analysis

作者:
Ziteng Cheng↗Sebastian Jaimungal↗

arXiv:2301.06930v5 Announce Type: replace-cross Abstract: In this paper, we use mean field games (MFGs) to investigate approximations of $N$-player games ($N$pGs) with uniformly symmetrically continuous heterogeneous closed-loop actions. To incorporate agents' risk aversion (beyond the classical expected utility of total costs), we use an abstract evaluation functional for their performance criteria. Centered around the notion of exploitability, we conduct non-asymptotic analysis on the approximation capability of MFGs from the perspective of state-action distributions without requiring the uniqueness of equilibria. Under suitable assumptions, we first show that scenarios in the $N$pGs with large $N$ and small average exploitabilities can be well approximated by approximate solutions of MFGs with relatively small exploitabilities. We then show that $\delta$-mean field equilibria can be used to construct $\varepsilon$-equilibria in $N$pGs. Furthermore, in this general setting, we prove the existence of mean field equilibria. This proof reveals a possible avenue for incorporating penalization for randomized action into MFGs.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CL) 2026-06-18

Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents

作者:
Emmanuel Aboah Boateng↗Kyle MacDonald↗Amardeep Kumar↗Siddharth Kodwani↗Sudeep Das↗

Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic boundary that moves grounding outside the reasoning model through an MCP-compatible gateway, exposing provider routing, source-aware context rendering, configured fallback, retrieval-depth control, and exact plus semantic caching as first-class controls. Across five frontier models on SimpleQA, FreshQA, and HotpotQA, native search leads on recency-sensitive FreshQA, but DSG exposes a stronger frontier when control matters: on SimpleQA it nearly matches native accuracy (86.1% vs. 87.7%) at 91% lower search cost, preserves concise answer contracts, and reaches a 99.4% warm-cache hit rate with 68% lower latency. Deployed as a shared production grounding layer for large-scale agentic workloads with interchangeable models, DSG matches or slightly exceeds native-search accuracy on an e-commerce query-understanding (QIU) workload while cutting search cost by over 98%. Real-time grounding is best treated as an optimizable interface boundary, not a fixed model feature.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CL) 2026-06-15

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA

作者:
Teng Chen↗Sheng Xu↗Feixiang Guo↗Xiaoyu Wang↗Qingqing Gu↗Hongyan Li↗Luo Ji↗

Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs. To address this limitation, we propose Rabtriever, which independently encodes queries and documents, while providing comparable cross query-document comprehension capabilities to rerankers. We start from training a LLM-based generative reranker, which puts the document prior to the query and prompts the LLM to generate the relevance score by log probabilities. We then employ it as the teacher of an on-policy distillation framework, with Rabtriever as the student to reconstruct the teacher's contextual-aware query embedding. To achieve this effect, Rabtriever is first initialized from the teacher, with parameters frozen. The Joint-Embedding Predictive Architecture (JEPA) paradigm is then adopted, which integrates a lightweight, trainable predictor between LLM layers and heads, projecting the query embedding into a new hidden space, with the document embedding as the latent vector. JEPA then minimizes the distribution difference between this projected embedding and the teacher embedding. To strengthen the sampling efficiency of on-policy distillation, we also add an auxiliary loss on the reverse KL of LLM logits, to reshape the student's logit distribution. Rabtriever optimizes the teacher's quadratic complexity on the document length to linear, verified both theoretically and empirically. Experiments show that Rabtriever outperforms different retriever baselines across diverse rationale-based tasks, including empathetic conversations and robotic manipulations, with minor accuracy degradation from the reranker. Rabtriever also generalizes well on traditional retrieval benchmarks such as MS MARCO and BEIR, with comparable performance to the best retriever baseline.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CL) 2026-06-11

PRInTS: Reward Modeling for Long-Horizon Information Seeking

作者:
Jaewoo Lee↗Archiki Prasad↗Justin Chih-Yao Chen↗Zaid Khan↗Elias Stengel-Eskin↗Mohit Bansal↗

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs - designed for short reasoning with binary judgment - cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon tasks. To address these limitations, we introduce PRInTS, a generative PRM trained with dual capabilities: (1) dense scoring based on the PRM's reasoning across multiple dimensions of step quality (e.g., interpretation of tool outputs, tool call informativeness) and (2) trajectory summarization that compresses the growing context while preserving essential information for step evaluation. Extensive evaluations across FRAMES, GAIA (levels 1-3), and WebWalkerQA (easy-hard) benchmarks on multiple models reveal that best-of-n sampling with PRInTS enhances information-seeking in open-source models as well as specialized agents, matching or surpassing frontier models with a much smaller backbone agent and outperforming other strong reward modeling baselines.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.LG) 2026-06-16

GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

作者:
Haotian Liu↗Yihao Liu↗Jingwei Ni↗Siyuan Huang↗Xinpeng Liu↗Pengyu Cheng↗Jiajun Song↗Ruijin Ding↗Junfeng Li↗Zhechao Yu↗Mengyu Zhou↗Hongteng Xu↗…

arXiv:2606.16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorithms capable of optimizing diverse and potentially competing objectives simultaneously. To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group. However, this strategy still encounters multi-reward conflicts: a single rollout can yield positive advantages on certain reward dimensions but negative ones on others, causing opposing signals to cancel each other out during aggregation, further hindering RL training efficiency. Inspired by Dynamic sAmpling Policy Optimization (DAPO), which improves RL training efficiency by filtering out ineffective rollouts with near-zero advantages, we propose Group-Dynamic reward-Decoupled Policy Optimization (GD$^2$PO). Specifically, GD$^2$PO employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement. By preventing conflicting signals from canceling each other out, this masking strategy preserves and enhances the magnitude of effective RL advantages, thereby significantly accelerating learning efficiency. Furthermore, we introduce query-level reweighting to dynamically adjust the update intensity of each query based on its overall reward consensus. Experiments on various multi-reward scenarios, including tool calling and human preference alignment, demonstrate that GD$^2$PO consistently and significantly outperforms existing baselines. The code is available at https://github.com/Qwen-Applications/GD2PO.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.AI) 2026-06-17

ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking

作者:
Hauteng Wu↗Xu Li↗Dong Kong↗Zihang Wang↗Xieyuanli Chen↗Benwu Wang↗Wenkai Zhu↗

arXiv:2606.17082v1 Announce Type: cross Abstract: End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving. However, existing methods suffer from black-box characteristics, lacking high-level semantic understanding and interpretability, which impedes the realization of seamless long-distance autonomous parking from the road to the target spot. To address these limitations, we propose ParkingTransformer, a novel framework that leverages multi-view perception and the scene understanding capability of Large Language Models (LLMs). By combining trajectory queries with LLMs implicit state features, our method interacts directly with historical information and raw sensor data to output planning trajectories, eliminating the need for dense Bird's-View (BEV) representations. To compensate for the inadequate spatial reasoning ability of LLMs, we introduce 3D positional encoding to explicitly inject spatial geometric awareness. Furthermore, a fixed-window streaming mechanism is designed for historical information processing, significantly improving long-term temporal processing efficiency and inference speed. Additionally, a coarse-to-fine decoding strategy is employed to progressively enhance trajectory precision. Extensive closed-loop experiments are conducted on the CARLA simulator and real-world vehicle platforms. The results demonstrate that our method achieves a driving score of 61.32 in CARLA simulator and an average success rate of 88.70% in real-world experiments, validating the feasibility and effectiveness of the proposed algorithms.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.LG) 2026-06-19

Pseudo-Formalization for Automatic Proof Verification

作者:
Slim Barkallah↗Luke Bailey↗Kaiyue Wen↗Mohammed Abouzaid↗Tengyu Ma↗

arXiv:2605.20531v2 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and modular. Most proofs, particularly those written by AI systems, have neither property, and translating them into formal languages remains challenging in many frontier math settings. We propose Pseudo-Formalization (PF), a proof format that captures the modularity and precision of formal proofs while retaining the flexibility of natural language. A Pseudo-Formal proof is decomposed into self-contained modules, each stating its premises, conclusion, and proof in natural language. To verify the correctness of a regular natural language proof, an LLM translates it to Pseudo-Formal and then verifies each module independently, an algorithm we call Block Verification (BV). We evaluate PF+BV on two benchmarks spanning olympiad and research-level mathematics, where it pareto-dominates LLM-as-judge baselines on error-finding precision and recall. To support future work, we release our research-level proof verification benchmark ArxivMathGradingBench.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CV) 2026-06-16

LentiAvatar: Pseudo-Multiview Reconstruction and Subpixel Prism Rendering for Real-Time Stereoscopic Communication

作者:
Chufeng Fang↗Dongdong Teng↗Lilin Liu↗

Real-time stereoscopic video communication has long been a goal of immersive telepresence, yet practical systems still require specialized capture rigs or reduce remote users to a single portrait view. We present LentiAvatar, a Gaussian head-avatar system that connects monocular avatar capture with subpixel-encoded glasses-free lenticular display for real-time autostereoscopic communication. From a monocular portrait video, LentiAvatar reconstructs a controllable head avatar and optimizes it for the lateral viewing zones induced by the display. The method uses natural head turns as pseudo-multiview (PMV) supervision to constrain regions that are otherwise weakly observed in monocular training, including hair, ears, jaw contours, and neck boundaries. Reliable side frames are yaw-binned, aligned to virtual cameras, and supervised within a strict head-and-hair domain; contour-aware losses and staged regularization further suppress ghosting, alpha leakage, and depth instability while preserving lateral detail. At runtime, LentiAvatar renders 32 virtual views and encodes them into a 4K lenticular raster with calibrated subpixel-routing masks. The live-tracker prototype sustains 10.65 FPS, and a subject-specific distilled driver raises the same display pipeline to 38.49 FPS.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.LG) 2026-06-18

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

作者:
Xuanfei Ren↗Tengyang Xie↗

arXiv:2606.18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes. We develop a statistical theory for offline policy optimization from such outcome-level supervision. We first study the canonical setting where the target remains the expected cumulative reward, but each offline trajectory provides only a scalar label whose conditional mean is the cumulative return. We propose OPAC, a pessimistic actor-critic algorithm that learns a latent reward model and optimizes a policy from trajectory-level labels. We prove a high-probability guarantee of order $\widetilde O(H^2\sqrt{C_{sa}(\pi^\star)/n})$ and a matching lower bound, characterizing the sharp statistical cost of replacing process-level rewards with one trajectory-level label. We then extend the principle to preference-based feedback, preserving the leading horizon and concentrability dependence up to preference-model constants. Finally, we study generalized outcome-based offline RL, where both the supervision and the objective are trajectory-level quantities induced by a nonlinear aggregation of latent per-step rewards. This problem is not learnable in general: for all-success objectives, any offline learner may require $\Omega(2^H)$ trajectories even with deterministic transitions and constant concentrability. We then identify a tractable regime through two structural coefficients, $\kappa_\mu(\sigma)$ and $\chi_\mu(\sigma)$, capturing information loss in outcome aggregation and generalized Bellman updates, under which generalized OPAC achieves polynomial sample complexity. Together, our results delineate when outcome-level supervision enables sample-efficient offline control and when missing process-level rewards create fundamental statistical barriers.

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

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

作者:
Shuai Wang↗Liang Li↗Yang Chen↗Ruopeng Gao↗Yao Teng↗Limin Wang↗

Unified Multimodal Models (UMMs) have emerged as a critical direction for general-purpose multimodal intelligence, integrating understanding and generation into a single framework. However, existing UMMs face prominent challenges: (1) the inherent learning conflicts between visual understanding and generation tasks, leading to suboptimal modeling in both tasks; (2) different understanding and generation visual spaces impeding scalability; (3) over-reliance on task-specific data that neglects the duality of text-image understanding and generation. To address these challenges, we propose UniDDT, which leverages a Noisy ViT encoder along with an LLM to unify semantic encoding for visual generation and understanding tasks, while employing a separate diffusion decoder to decouple diffusion decoding from text decoding. With this Noisy ViT encoder, UniDDT is able to leverage the latent space as a unified visual representation, enabling seamless compatibility between understanding and generation tasks. Thus, the scalability within the generation tasks and the semantic expressiveness within understanding tasks can be balanced. Also, we construct dual data structures from the same image-text pairs, fostering interdependence between the generation and understanding data to exploit their inherent duality. Extensive experiments demonstrate that UniDDT achieves effective unification of multimodal understanding and generation with enhanced semantic consistency and scalability. For visual generation tasks, our UniDDT achieves 0.87 GenEval score and 86.9 DPG overall score. For multimodal understanding tasks, our UniDDT achieves 1699.5 score on MME benchmark and 76.5 overall score on SEEDbench.

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

HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling

作者:
Jonathan Cederlund↗Axel Berg↗William Isaksson↗Durmus Alp Emre Acar↗Chuteng Zhou↗Pontus Giselsson↗

Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated image. We introduce HeatKV, a novel compression method that adapts cache allocation in each head based on its attention to previously generated scales. Using a small offline calibration set, the attention heads are ranked according to their attention scores over prior scales. Based on this ranking, we construct a static pruning schedule tailored to a given memory budget. Applied to the Infinity-2B model, HeatKV achieves $2 \times$ higher compression ratio in memory allocation for KV cache compared to existing methods, while maintaining similar or better image fidelity, prompt alignment and human perception score. Our method achieves a new state-of-the-art (SOTA) for VAR model KV-cache compression, showcasing the effectiveness of fine-grained, head-specific cache allocation. Code and calibration script available at https://github.com/arm-research/heatkv.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-12

CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation

作者:
Yuheng Chen↗Teng Hu↗Yuji Wang↗Qingdong He↗Zhucun Xue↗Qianyu Zhou↗Jason Li↗Lizhuang Ma↗Jiangning Zhang↗Dacheng Tao↗

The fidelity and structural diversity of training datasets fundamentally determine the capabilities of video generation models. While commercial systems showremarkableabilitytogeneratecinematicnarratives, the progress of open-source models remains limited by the scarcity of high-quality training data. To bridge this gap, we introduce CineDance-1M, a large-scale, open research Text-to-Audio-Video (T2AV) dataset designed specifically for multi-shot, long-form joint audio-video generation. Averaging 92.8 seconds and 24.2 continuous shots per video, it provides configurable, structured annotations for both audio and video modalities. This exceptional quality is achieved through a rigorous three-stage curation pipeline: i) diverse sourcing and comprehensive cleansing, ii) film-theory-inspired narrative parsing, and iii) hierarchical dual-modal captioning. For a comprehensive assessment, we propose CineBench, featuring a diverse prompt suite and a six-dimensional, human-aligned metric system tailored for complex narrative audio-video evaluation. Furthermore, we adapt LTX-2.3 into CineDance, which demonstrates exceptional single-modality quality alongside precise audio-video alignment and robust subject and environment consistency, effectively validating our curation strategy and the high quality of CineDance-1M. We anticipate that this work will serve as a solid foundation for accelerating future research in multi-shot, long-form joint audio-video generation. Our project page is available at https://aliothchen.github.io/projects/CineDance/.

阅读与讨论 → 访问原文 →