中 EN
Sign In Register
×

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
Authors: Sun ×
↻ Shuffle
01.
medRxiv (Medicine) 2026-06-22

The direct economic impact of surgical non-response in orthopaedic hip, knee, and spine surgery for osteoarthritis: a cost-utility analysis

Authors:
Rampersaud↗Y. R↗Perruccio↗A. V↗Collett↗Sundararajan↗Du↗J. T↗Montoya↗Power↗J. D↗Canizares↗…

Background Annually, nearly 2 million hip, knee, and spinal inpatient surgeries are performed in Canada and the US for osteoarthritis (OA), costing over $37 billion in hospital expenditures. However, 15-30% of patients experience limited or no improvement, resulting in poor value for money. This study evaluated the one-year cost-utility of joint and spine procedures for OA by comparing non-responders to responders, considering various responder definitions. Methods Individual micro-costing data were collected for 1,175 elective hip, knee, and spine patients enrolled in the Longitudinal Evaluation in the Arthritis Program - Osteoarthritis (LEAP-OA) between 2014 and 2018. Quality-adjusted life years (QALYs) were derived using the SF-6D utility index. One-year incremental cost-utility ratios (ICURs) were calculated from the hospital perspective. Results Responder rates varied by definition, ranging from 78%-94% for hip replacements, 64%-90% for knee replacements, 60%-64% for spine fusions, and 50%-68% for spine decompressions. Corresponding ICURs were: $45,956-$51,773/QALY for responders versus $108,593-$485,762/QALY for non-responders for hip replacements; $54,831-$71,151/QALY for responders versus $200,486-$1,203,596/QALY for non-responders for knee replacements; $65,980-$74,422/QALY for responders versus $262,039-$729,686/QALY for non-responders for spine fusions; and $29,947-$42,168/QALY for responders versus $63,195-$662,586/QALY for non-responders for spine decompressions. Conclusions While surgical response rates were highly dependent on the responder definition, ICURs for non-responders were significantly higher than those for responders across all definitions. Beyond the negative impact on patients, there is a compelling economic argument for investment in improved pre-operative identification of patients at risk of surgical non-response. Such efforts could enable more personalized, value-based care pathways and reduce the provision of low-value surgical interventions.

Read & Discuss → View Source →
02.
arXiv (math.PR) 2026-06-15

Secondary terms for first moments of Selmer groups of twists of elliptic curves over global function fields

Authors:
Sun Woo Park↗

arXiv:2606.14274v1 Announce Type: cross Abstract: Let $E$ be a non-isotrivial elliptic curve over a global function field $\mathbb{F}_q(t)$ of characteristic coprime to $2$ and $3$. Under some explicit conditions, we determine the secondary terms for the first moments of prime Selmer groups of cyclic prime twist families of $E$ over $\mathbb{F}_q(t)$.

Read & Discuss → View Source →
03.
arXiv (CS.CV) 2026-06-17

Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification

Authors:
Haoyu Zhang↗Yuwei Wu↗Pengxiang Li↗Xintong Zhang↗Zhi Gao↗Rui Gao↗Mingyang Gao↗Che Sun↗Yunde Jia↗

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or logic errors. Existing VLMs often produce plausible yet ungrounded answers, and even when prompted to "reflect", their corrections may remain detached from the image evidence. To address this, we propose the MIRROR framework for Multimodal Iterative Reasoning via Reflection On visual Regions. By embedding visual reflection as a core mechanism, MIRROR is formulated as a closed-loop process comprising draft, critique, region-based verification, and revision, which are repeated until the output is visually grounded. To facilitate training of this model, we construct **ReflectV**, a visual reflective dataset for multi-turn supervision that explicitly contains reflection triggers, region-based verification actions, and answer revision grounded in visual evidence. Experiments on both general vision-language benchmarks and representative vision-language reasoning benchmarks show that MIRROR improves correctness and reduces visual hallucinations, demonstrating the value of training reflection as an evidence-seeking, region-aware verification process rather than a purely textual revision step.

Read & Discuss → View Source →
04.
arXiv (CS.CL) 2026-06-17

Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings

Authors:
Ryo Fukuda↗Takatomo Kano↗Siddhant Arora↗Marc Delcroix↗Naohiro Tawara↗Atsunori Ogawa↗Yuya Chiba↗Atsushi Ando↗William Chen↗Shinji Watanabe↗

We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, turn-change prediction, and next speaker prediction. We compare supervised models trained for these tasks, text-based LLMs, multimodal LLMs (MM-LLMs), and human subjects. Experiments on the AMI corpus showed that LLMs outperformed supervised models and humans in next speaker prediction, despite not being trained on the target domain and without access to audio or visual information. An MM-LLM performed better than text-based LLMs on addressee detection and turn-change prediction but remained below human performance, indicating difficulty leveraging raw audio-visual signals. Ablation analyses revealed that conversational context was critical, particularly for next speaker prediction. We observed that human and LLM prediction patterns were similar, and intervals with frequent turn changes were difficult for both.

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-16

XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

Authors:
Yupei Li↗Qiyang Sun↗Xiaoliang Wu↗Chenxi Wang↗Berrak Sisman↗Bj\"orn W. Schuller↗

Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making. Existing explanation ways mainly fall into two categories. Traditional explainable AI (XAI), such as gradient-based attribution, produces low-level attribution signals tightly coupled with model decisions, and harder to be understood by human than natural language explanations. Meanwhile, large language model (LLM)-based explanation generation often produces generic and ungrounded descriptions due to the lack of heuristic evidence and task-specific supervision, stemming from limited grounded explanation datasets for SDD. We therefore propose a training-free explanation framework that integrates XAI evidence with multimodal LLMs to generate grounded and specific explanations. Using the PartialSpoof dataset, we construct a grounded explanation dataset and show that methods with XAI increase inside accuracy by over 45\%, verified through human evaluation and faithfulness checks.

Read & Discuss → View Source →
06.
arXiv (CS.CL) 2026-06-15

Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback

Authors:
Woohyeon Byeon↗Jiwon Jeon↗Jeonghye Kim↗Youngchul Sung↗

We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback. Unlike one-way distillation or single-model fine-tuning, our goal is mutual Pareto improvement: each model improves across domains without losing its original strength. To this end, we propose On-Policy Co-Distillation (OPCoD), where each student's self-distillation is conditioned on its own correct rollout and feedback from its peer. To make feedback exchange effective, OPCoD uses cognizance-based gating to decide when to give feedback and feedback anchoring to ground feedback in the problem. On Science Q\&A tasks, OPCoD consistently outperforms baselines and achieves Pareto improvement across all evaluated domain pairs and students.

Read & Discuss → View Source →
07.
arXiv (CS.CL) 2026-06-25

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

Authors:
Lianbo Liu↗Shiao Zhu↗Kai Washizaki↗Reo Yoneyama↗Haesung Jeon↗Mengjie Zhao↗Yusuke Fujita↗Hao Shi↗Nao Yoshida↗Yuan Gao↗Roman Koshkin↗Yukiya Hono↗…

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k hours of speech, incorporating a balanced mix of Japanese and English data. Furthermore, we design a targeted data augmentation pipeline covering all 2,136 Joyo (regular-use) kanji designated by Japan's Agency for Cultural Affairs to efficiently address kanji polyphony disambiguation. Second, we introduce the Joyo Kanji Yomi Benchmark (https://github.com/sbintuitions/JoyoKanji-Yomi-Benchmark), covering all 2,136 Joyo kanji and their 4,378 readings. Alongside this benchmark, we propose Kana-CER, a metric that compares synthesized speech against reference readings in the kana space, eliminating orthographic variations to directly measure pronunciation correctness. Experiments demonstrate that our targeted data augmentation significantly improves reading accuracy. Overall, Sarashina2.2-TTS achieves state-of-the-art kanji-level reading accuracy and matches top baselines on general sentence-level pronunciation, while delivering the highest speaker similarity in zero-shot Japanese speech synthesis. Furthermore, cross-lingual evaluation reveals that Sarashina2.2-TTS is the only system that maintains stable Japanese pronunciation regardless of the prompt language, confirming that our balanced training approach improves cross-lingual robustness.

Read & Discuss → View Source →
08.
arXiv (CS.CV) 2026-06-24

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

Authors:
Xingsong Ye↗Yongkun Du↗Jiaxin Zhang↗Haojie Zhang↗Chong Sun↗Chen Li↗Jing Lyu↗Zhineng Chen↗

WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing STR datasets and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER. Thus, we aim to advance this task from both data and model perspectives. On the data side, we construct a 2M synthetic dataset, WATER-S, with the scale improved by hundreds of times compared to existing artistic text data. WATER-S consists of two complementary subsets. One rendered by an upgraded rendering pipeline (SynthWordArt), which provides highly accurate and controllable synthetic WordArt data. The other is generated by combining Qwen3-VL for prompt mining and Z-Image for image synthesis, which improves the coverage of realistic and diverse data. On the model side, we propose WATERec. It adopts an visual encoder supporting arbitrary-shaped inputs and an autoregressive decoder to model complex layouts, structurally breaking the bottleneck of fixed-template STR on WordArt. Experiments show that this architecture outperforms prior STR methods, achieving state-of-the-art performance on irregular texts such as WordArt. Together with WATER-R, carefully reorganized from existing real STR data, our strong baseline with the new synthetic data and model design reaches 90.40% accuracy on WordArt-Bench, surpassing both general-purpose and OCR-specialized vision-language models by a large margin. Code and data are available at https://github.com/YesianRohn/WATER.

Read & Discuss → View Source →
09.
arXiv (CS.AI) 2026-06-11

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

Authors:
Tsung-En Lin↗Hung-Yi Lee↗

arXiv:2606.11400v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend. We introduce instruction-based vector steering, which constructs a steering vector by contrasting activations from differently instructed prompts while keeping the audio fixed. Through a systematic probe of LALM attention, we find that - unlike standard prompting or audio-based steering - this intervention significantly redistributes the temporal attention allocated to audio tokens, concentrating it on acoustically relevant regions. We then show that this attention shift is behaviorally meaningful: in a controlled three-event setting, reading out the temporal position of maximal steering-induced attention change recovers the location of a queried sound event without any training, attaining 60.87% and 68.72% overlap with ground-truth intervals on Qwen2-Audio and Audio Flamingo 3, far above direct prompting (31.84%, 46.75%) and random baselines (27.74%). Our results characterize a mechanistic property of instruction-based steering in LALMs and provide a training-free probe for the latent temporal structure these models encode.

Read & Discuss → View Source →
10.
arXiv (CS.CL) 2026-06-18

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents

Authors:
Xiaohui Zhang↗Zequn Sun↗Chengyuan Yang↗Yaqin Jin↗Yazhong Zhang↗Wei Hu↗

Memory management is essential for LLM agents in long-term interactions. Current memory frameworks typically treat agents as passive ``recorders'' and retrieve information without understanding its deeper implications. They may fail in scenarios requiring reasoning and complex decision-making. To bridge this critical gap, we propose a novel actionable memory framework called ActMem that integrates memory retrieval with active causal reasoning. ActMem transforms unstructured dialogue history into a structured causal and semantic graph. By leveraging counterfactual reasoning and commonsense completion, it enables agents to deduce implicit constraints and resolve potential conflicts between past states and current intentions. Furthermore, we introduce a comprehensive dataset ActMemEval to evaluate agent reasoning capabilities in logic-driven scenarios, moving beyond the fact-retrieval focus of existing memory benchmarks. Experiments demonstrate that ActMem significantly outperforms baselines in handling complex, memory-dependent tasks, paving the way for more consistent and reliable intelligent assistants.

Read & Discuss → View Source →
11.
arXiv (CS.AI) 2026-06-24

Skills for the future software profession: beyond agentic AI!

Authors:
Sungmin Kang↗Baishakhi Ray↗Abhik Roychoudhury↗

arXiv:2606.21894v2 Announce Type: replace-cross Abstract: As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineers? To identify where software engineering is headed and thus what skills will be needed, we summarize the results of two round-tables with researchers and industrial practitioners, held in 2026 in New York and Singapore. One key finding is that verification and validation is increasing in importance as agents handle implementation, as highlighted by anecdotes from the events. From our observations, we identify the skills developers need in the agentic era of development, with implications for training and educating future software engineers in coming years.

Read & Discuss → View Source →
12.
arXiv (CS.CV) 2026-06-16

DDTNet: Degradation Disentanglement and Transfer Network for Test-Time All-in-One De-weathering Adaptation

Authors:
Kuan-Hung Lin↗Fu-Jen Tsai↗Yan-Tsung Peng↗Min-Hung Chen↗Chia-Wen Lin↗Yen-Yu Lin↗

All-in-one adverse weather image restoration aims to remove multiple degradations, such as rain, haze, and snow, using a single unified model. Despite their broad applicability, existing methods typically compromise performance, delivering balanced but suboptimal results for individual degradation types. This issue becomes more pronounced when a domain gap exists between training and testing data. Motivated by the observation that modeling degradation patterns is more feasible than recovering clean content, we propose the Degradation Disentanglement and Transfer Network (DDTNet), which focuses specifically on degradation transfer. By disentangling degradation patterns from target-domain degraded images and transferring them to source domain clean images, DDTNet generates domain-adaptive paired training data. These pairs are then used to fine-tune restoration models, significantly enhancing their adaptability across diverse weather conditions and domains. The core of DDTNet is the Degradation Disentanglement Module (DDM), which comprises Degradation Coupled Attention (DCA) to capture both general and weather-specific features, thereby enabling effective disentanglement and transfer of degradation patterns. Experimental results demonstrate that DDTNet significantly and consistently improves existing all-in-one models across real-world deraining, desnowing, and dehazing datasets.

Read & Discuss → View Source →
13.
arXiv (CS.LG) 2026-06-25

Auto-Configured Explainable Graph Neural Networks for Multi-Site Pollution Prediction

Authors:
Abdelkader Dairi↗Fouzi Harrou↗Ying Sun↗

arXiv:2606.24978v1 Announce Type: new Abstract: Accurate particulate matter (PM) prediction is crucial for mitigating air pollution. Graph Neural Networks (GNNs) effectively model spatiotemporal dependencies, but predefined graphs limit adaptability, and some datasets complicate learning. This study introduces a graph construction method based on a confusion matrix from a supervised learning process to dynamically capture inter-class relationships. Additionally, a hybrid loss function that combines energy distance and Huber loss is applied to address the vanishing gradient problem and improve learning stability. The approach is evaluated using air pollution data from the University of Utah AirU Pollution Monitoring Network in Salt Lake City, UT, with five GNN models: Graph Convolutional Networks (GCNs), Simple Graph Convolutional Networks (SGConv), Graph Isomorphism Networks (GINs), Graph Attention Networks (GATs), and GraphSage. The experimental results of single- and multistep predictions confirm that GraphSage achieves the highest accuracy in predicting the concentrations of PM${1}$, PM${10}$, and PM$_{2.5}$ over different time horizons. Furthermore, {\color{black} GNNExplainer (Graph Neural Network Explainer) and PGExplainer (Probabilistic Graph Explainer)} are applied to interpret feature importance and graph structure, ensuring model transparency. Results show improved prediction accuracy, with GNN models outperforming traditional machine learning \textcolor{black}{and deep learning models (i.e., Prophet, Long short-term memory, Gated recurrent units} in air pollution forecasting.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting

Authors:
Seunghan Lee↗Jaehoon Lee↗Jun Seo↗Sungdong Yoo↗Minjae Kim↗Tae Yoon Lim↗Dongwan Kang↗Hwanil Choi↗SoonYoung Lee↗Wonbin Ahn↗

arXiv:2603.14709v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance when fusing retrieved samples with the query. We argue that not all retrievals are equally useful, and irrelevant ones can degrade performance. To this end, we propose Cross-RAG, a zero-shot RAG-based forecasting framework that selectively attends to query-relevant retrieved samples via query–retrieval cross-attention. By modeling input-level relevance between the query and retrieved samples, Cross-RAG jointly incorporates three sources of information: 1) the query itself, 2) the retrieved samples, and 3) their relational interactions. In particular, this input-aware design enables Cross-RAG to remain stable as the number of retrieved samples $k$ grows, whereas prior methods without cross-attention require careful $k$ tuning to avoid degradation from irrelevant retrievals. Extensive experiments demonstrate that Cross-RAG consistently improves zero-shot forecasting performance across multiple TSFM backbones and various RAG methods, with additional analyses confirming its effectiveness across various retrieval scenarios. Code is available at https://github.com/seunghan96/cross-rag/.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-17

StepGuard: Guarding Web Navigation via Single-Step Calibration

Authors:
Zhihao Cui↗Yuchen Zhang↗Xiyang Sun↗Yaxiong Wang↗Li Zhu↗Jinpeng Hu↗Liu Liu↗Mengjia Li↗Yujiao Wu↗

arXiv:2606.17871v1 Announce Type: new Abstract: Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confidence-Guided Adaptive Navigation Reflection (CANR), a mechanism that estimates per-step confidence, triggers reflection only when necessary, and uses contrastive rewards to encourage self-correction to calibrate the single-step inaccuracy. With the above as the main components, we finally develop our StepGuard, a new framework of Guarding Web Navigation via Single-Step Calibration. Experiments demonstrate that our approach significantly improves navigation and answer accuracy, setting new state-of-the-art performance on standard web navigation benchmarks.

Read & Discuss → View Source →
16.
arXiv (CS.CV) 2026-06-15

Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation

Authors:
Yu He↗Da Huang↗Zhenyang Liu↗Zixiao Gu↗Qiang Sun↗Guangnan Ye↗Yanwei Fu↗Yu-Gang Jiang↗

Zero-shot object navigation (ZSON) requires robots to find target objects in unseen environments without task-specific fine-tuning or pre-built maps, a key capability for general-purpose service robots. Yet methods that perform well in simulation often degrade in cluttered real-world scenes with severe occlusion and latent hazards, where large unseen regions make single-scene inference brittle and unsafe. We propose Schrödinger's Navigator, a belief-aware framework that reasons at inference time over multiple trajectory-conditioned imagined 3D futures. Given candidate paths, a trajectory-conditioned 3D world model predicts hypothetical observations and maintains a superposition of plausible scene realizations rather than committing to one map. An adaptive occluder-aware sampler directs imagination to uncertainty-critical regions, while a Future-Aware Value Map (FAVM) aggregates imagined futures for robust, proactive action selection. Experiments in simulation and on a physical Go2 quadruped show that Schrödinger's Navigator outperforms strong ZSON baselines, improving hidden-target discovery and risk-aware waypoint selection in occlusion-heavy navigation scenarios. These results highlight imagined 3D futures as a scalable and generalizable strategy for zero-shot navigation in uncertain real-world environments.

Read & Discuss → View Source →
17.
arXiv (CS.CV) 2026-06-17

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

Authors:
Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

Read & Discuss → View Source →
18.
arXiv (CS.LG) 2026-06-17

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Authors:
Lingjing Kong↗Xin Liu↗Guangyi Chen↗Martin Q. Ma↗Xiangchen Song↗Yuekai Sun↗Mikhail Yurochkin↗Taylor W. Killian↗Ruslan Salakhutdinov↗Kun Zhang↗Eric P. Xing↗Zhengzhong Liu↗…

arXiv:2606.18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

Read & Discuss → View Source →
19.
arXiv (CS.CV) 2026-06-16

MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers

Authors:
Maoliang Li↗Haojing Chen↗Jiayu Chen↗Zihao Zheng↗Xinhao Sun↗Hailong Zou↗Xiang Chen↗

Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation across timesteps. Existing caching methods mainly operate at the token level, which becomes suboptimal in DiT-MoE because each token update is internally decomposed into multiple routed expert branches. Our analysis shows that cross-timestep redundancy in DiT-MoE is better characterized at the expert-branch level than at the whole-token level. Based on this observation, we propose MoECa, a fine-grained caching framework that performs branch-level feature reuse across timesteps. MoECa further introduces expert-aware adaptive control and synchronized cache updates across MoE and attention paths to maintain stable intermediate states. Experiments on multiple DiT-MoE models show that MoECa consistently achieves a better speed-quality trade-off than prior caching methods, with up to 2.83$\times$ inference speedup and minimal quality degradation.

Read & Discuss → View Source →
20.
arXiv (CS.CV) 2026-06-18

Cosmos 3: Omnimodal World Models for Physical AI

Authors:
NVIDIA↗Aditi↗Niket Agarwal↗Arslan Ali↗Jon Allen↗Martin Antolini↗Adeline Aubame↗Alisson Azzolini↗Junjie Bai↗Maciej Bala↗Yogesh Balaji↗Josh Bapst↗…

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

Read & Discuss → View Source →
21.
arXiv (CS.CV) 2026-06-16

DenseControl: Instance-Level Controllable Synthesis of Dense Crowd Image

Authors:
Juncheng Wang↗Lei Shang↗Wang Lu↗Baigui Sun↗Shujun Wang↗

In this paper, we introduce DenseControl, a novel pipeline for generating dense crowd images. Specifically, DenseControl meticulously positions and sizes each generated instance to align precisely with the predefined coordinates and scales. Based on this, we further allow for control over the background, style, and attributes of instances. The motivation behind DenseControl stems from the observation of two main challenges in synthesizing crowd images: controlling signal embedding and maintaining topological integrity when imparting instance scale guidance. To address these, we first introduce the Isolated Object Embedding (IOE) map, a novel representation that facilitates spatial location control while mitigating the difficulties associated with learning projections for model. Secondly, we propose an Implicit Scale Embedding (ISE) strategy that seamlessly integrates with the IOE map to encode precise scale information. To further enhance the efficacy of combining ISE with the IOE map, we incorporate a Position Shortcut mechanism that enhances cross-attention to alleviate projection challenges. We evaluate DenseControl through two lenses: synthesis quality and applicability in latent applications. Experiments across different control conditions demonstrate DenseControl achieves state-of-the-art results in dense crowd image synthesis. Furthermore, we showcase applications in augmenting crowd analysis under data scarcity, transfer learning, and weather generalization scenes, to highlight the practical utility of DenseControl. The codebase will be released.

Read & Discuss → View Source →
22.
arXiv (CS.CV) 2026-06-16

EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP–OCT Pretraining

Authors:
Zhuo Deng↗Ruiheng Zhang↗Ziheng Zhang↗Weihao Gao↗Yitong Li↗Qian Wang↗Lei Shao↗Jiaoyue Dong↗Zhixi Zeng↗Lijian Fang↗Haibo Wang↗Xiaobin Lin↗…

Color fundus photography (CFP) is the mainstay for large-scale retinal screening, yet its diagnostic capacity is constrained by the lack of depth-resolved structural information. Optical coherence tomography (OCT) provides cross-sectional retinal anatomy, but is less accessible in population-level screening. Here, we present EyeMVP, a cross-modal retinal foundation model that uses paired CFP–OCT pretraining to learn OCT-informed CFP representations. EyeMVP is pretrained on 674,893 strict same-eye same-day paired CFP–OCT image triples from 112,642 patients across eight hospitals in China. The model uses cross-modal masked reconstruction to enrich CFP representations with OCT-associated supervision, while requiring only CFP images at inference. To accommodate the non-aligned imaging geometry between en-face CFP and cross-sectional OCT, EyeMVP combines source-constrained cross-attention with CFP-derived structural masks. Across 16 downstream tasks, including classification, segmentation, few-shot adaptation, and cross-modal retrieval, EyeMVP outperforms representative retinal foundation models and shows consistent gains on tasks involving macular and optic nerve structure. For CFP-challenging macular diseases, EyeMVP achieves an AUROC of 0.948 for macular edema (vs.~0.852 for EyeCLIP) and 0.825 for myopic macular schisis. In an exploratory reader study, EyeMVP exceeds junior and intermediate ophthalmologist groups but does not reach senior ophthalmologist performance on macular edema, while showing numerically higher balanced accuracy than all reader groups on myopic macular schisis. These results suggest that pixel-level cross-modal reconstruction can enrich CFP representations with OCT-associated supervision, providing a practical route toward stronger CFP-based retinal analysis in screening settings.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-18

Robust Regularized Policy Iteration under Transition Uncertainty

Authors:
Hongqiang Lin↗Zhenghui Fu↗Weihao Tang↗Pengfei Wang↗Yiding Sun↗Qixian Huang↗Dongxu Zhang↗

arXiv:2603.09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate and derives an efficient policy iteration procedure based on a robust regularized Bellman operator. We provide theoretical guarantees by showing that the proposed operator is a $\gamma$-contraction and that iteratively updating the surrogate yields monotonic improvement of the original robust objective with convergence. Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines including percentile-based methods on the majority of environments while remaining competitive on the rest. Moreover, RRPI exhibits robust performance by aligning lower $Q$-values with high epistemic uncertainty, which prevents the policy from executing unreliable out-of-distribution actions.

Read & Discuss → View Source →
24.
arXiv (CS.AI) 2026-06-19

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

Authors:
Fanfu Xue↗En Yu↗Yantian Shen↗Zhikun Hu↗Hongjun Wang↗Yang Yang↗Xindi Wang↗Jiande Sun↗

arXiv:2606.20045v1 Announce Type: cross Abstract: UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce UAV-VLN-FOV, a target-visible navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a vision-language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and geometric details for target grounding. It also updates the target-relative direction online during closed-loop navigation, allowing the agent to maintain spatial alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive UAV-VLN baselines, achieving a 13.82\% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach navigation. The source code and benchmark are available at https://github.com/xuefanfu/3DG-VLN.

Read & Discuss → View Source →
25.
arXiv (CS.AI) 2026-06-24

Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

Authors:
Ayan Antik Khan↗Harsh Kohli↗Yuekun Yao↗Huan Sun↗Ziyu Yao↗

arXiv:2606.24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize. In this work, we study whether language model (LM) agents can assist with this explanation problem once a circuit has already been identified. We introduce AgenticInterpBench, a benchmark for circuit explanation built from 84 semi-synthetic transformer circuits with 163 component-level annotations. We propose HyVE (Hypothesize, Validate, Explain), an agentic explainer that analyzes each component through an iterative loop of observation, hypothesis generation, and causal validation, eventually producing a component-level explanation and a circuit-level task description. Across four LM backbones, HyVE recovers useful component- and task-level explanations, but no backbone is uniformly best. Our analysis shows that strong backbones usually form observation-grounded hypotheses, while failures more often arise later in the validation loop, through incomplete validation plans, code execution errors, or unresolved hypotheses. A case study on an arithmetic circuit in Llama-3-8B shows that the same formulation can extend beyond semi-synthetic benchmarks to naturally trained models. Overall, LM agents are promising circuit explainers, but reliable validation remains the key obstacle.

Read & Discuss → View Source →