❌

Reading view

↗️

Impact of LLM-supported patient education on patient perspectives and patient-reported outcomes: a mixed-methods systematic review

✇npj Digital Medicine
By: Jiayi Liu · Yanan Zhang · Honghao Lai · Min Han · Ning Ma · Sibo Du · Weilong Zhao · Danni Xia · Bo Tong · Yanru Liu · Bei Pan · Xiaoman Wang · Bingyi Wang · Xufei Luo · Yimeng Li · Janne Estill · Sheng Li · Hongfei Cui · Li Xiao · Long Ge

npj Digital Medicine, Published online: 10 September 2026; doi:10.1038/s41746-026-03228-7

Impact of LLM-supported patient education on patient perspectives and patient-reported outcomes: a mixed-methods systematic review
  •  
  • ↗️
↗️

Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements

✇cs.AI, q-bio.NC updates on arXiv.org
By: Oliver G. B. Garrod · Robin A. A. Ince · Meng Liu · Mohamed Huti · Moritz Boos · Amy Waldock · Dominic Andrews · Paul Atherton
arXiv:2609.09425v1 Announce Type: cross Abstract: Educational data filters have become a practical way to improve language-model pre-training, but most filters treat educational value as a single scalar property. This may be too broad for some applications, especially if the data set already features a high density of educational material. Useful learning material needs to be accurate, engaging, well structured, and appropriate for the intended audience and application (e.g. learner- vs teacher-facing). Following QuRating (Wettig et al. 2024), we introduce Edu-QuRating: a pipeline for multi-dimensional educational data scoring and curation. Edu-QuRating defines education-specific rubrics, uses an LLM judge to label sampled document pairs and distills those pairwise preferences into reusable Edu-QuRaters, which can score individual text chunks on a set of educational criteria. Across two sequence-classification base models and six educational criteria, the best Edu-QuRater recovers held-out GPT-4.1-mini pairwise judgements with mean accuracy 0.917. We then apply the resulting scorers in two applications. First, we investigate the potential of Edu-QuRaters for corpus filtering to improve pretraining of small language models. We scored 322.25M FineWeb-Edu-Fortified documents to obtain a filtered pre-training mixture. In matched single-run pre-training comparisons, models trained with Edu-QuRating-based mixtures reached higher observed aggregate accuracy across nine benchmarks than the FineWeb-Edu baseline, with gains concentrated in particular tasks. Second, we used Edu-QuRater scores as reward terms for GRPO post-training. In held-out pairwise judge evaluations, combining Edu-QuRater and answer-structure rewards produced responses preferred to the Qwen3-4B base model on both pedagogical quality and instruction following.
  •  
  • ↗️
↗️

Synergistic Vision-Language Reinforcement Enables Scalable On-Demand Analysis across Diverse Clinical Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haonan Wang · Jiaji Mao · Lehan Wang · Qixiang Zhang · Marawan Elbatel · Yi Qin · Huijun Hu · Baoxun Li · Wenhui Deng · Weifeng Qin · Hongrui Li · Jialin Liang · Jun Shen · Xiaomeng Li
arXiv:2505.03380v2 Announce Type: replace-cross Abstract: Accurate delineation of tumors and surrounding organs-at-risk is essential for radiotherapy, surgery and treatment response assessment, yet remains time-consuming and expertise-intensive. Existing artificial intelligence systems often require manual spatial prompts or task-specific retraining, while generic class labels provide limited semantic grounding for heterogeneous disease targets. Here we present SyRe, a promptable segmentation foundation model based on Synergistic vision-language Reinforcement. SyRe strengthens bidirectional interaction between visual and linguistic representations to improve semantically grounded spatial understanding. To support large-scale training, we introduce the Color Region Description strategy and construct SyReData, comprising 20 million image-mask-description triplets across 9 modalities and 229 segmentation tasks. Training with diversified prompt forms further enables open-ended prompting, invalid-prompt rejection and flexible switching between single- and multi-target analysis. SyRe achieves accurate text-prompted segmentation across diverse clinical scenarios, with particularly strong performance on disease-related targets. Across 28 unseen external datasets, including 20 cancer types and multinational in-house cohorts, SyRe generalizes robustly under real-world distribution shifts. SyRe-generated masks also preserve clinically relevant quantitative information in pathology and yield radiomics features that stratify survival and improve prognostic modeling across five retrospective CT and MRI tumor cohorts. Finally, clinician-in-the-loop refinement enables efficient case-level correction when greater precision is required. These results establish SyRe as a generalizable foundation for scalable quantitative oncology and clinician-guided segmentation refinement.
  •  
  • ↗️
↗️

L2IR: Revealing Latent Intent in Graph Fraud Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jinsheng Guo · Zhenhao Weng · Yibo Liu · Yan Qiao · Meng Li
arXiv:2605.26040v1 Announce Type: new Abstract: Graph fraud detection has long depended on Graph Neural Networks (GNNs) to propagate and aggregate information across relational data. A critical obstacle in practice, however, is that fraudsters frequently disguise themselves by forging numerous connections with benign users, causing fraud signals to be progressively diluted during neighborhood aggregation and undermining detection reliability. While recent efforts have used Large Language Models (LLMs) to provide rich semantic cues for fraud detection, the underlying intent behind suspicious connections remains insufficiently explored. Compounding this issue, the scarcity of annotated fraud samples makes it difficult to train detectors that remain robust under heavy camouflage. To address these gaps, we propose L2IR, an LLM-driven Latent Intent Revealing framework for graph fraud detection. By uncovering latent intent from both user behaviors and suspicious connections, L2IR extracts intent-aware representations from raw behavioral traces and reasons about the true purpose behind individual connections, effectively distinguishing supportive links from misleading ones. It further incorporates adaptive self-training to enhance robustness under limited supervision. Evaluations on two real-world datasets characterized by pervasive camouflage demonstrate that L2IR surpasses strong baselines and can function as a plug-in enhancement for a range of GNN-based detectors, improving AUPRC by up to 8.27%.
  •  
  • ↗️
↗️

Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhexi Lian · Haoran Wang · Xuerun Yan · Weimeng Lin · Xianhong Zhang · Yongyu Chen · Jia Hu
arXiv:2603.13842v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL) through sequential fine-tuning. However, such a paradigm remains suboptimal: sequential RL fine-tuning can introduce policy drift and often leads to a performance ceiling due to its dependence on the pretrained IL policy. To address these issues, we propose PaIR-Drive, a general Parallel framework for collaborative Imitation and Reinforcement learning in end-to-end autonomous driving. During training, PaIR-Drive separates IL and RL into two parallel branches with conflict-free training objectives, enabling fully collaborative optimization. This design eliminates the need to retrain RL when applying a new IL policy. During inference, RL leverages the IL policy to further optimize the final plan, allowing performance beyond prior knowledge of IL. Furthermore, we introduce a tree-structured trajectory neural sampler to group relative policy optimization (GRPO) in the RL branch, which enhances exploration capability. Extensive analysis on NAVSIMv1 and v2 benchmark demonstrates that PaIR-Drive achieves Competitive performance of 91.2 PDMS and 87.9 EPDMS, building upon Transfuser and DiffusionDrive IL baselines. PaIR-Drive consistently outperforms existing RL fine-tuning methods, and could even correct human experts' suboptimal behaviors. Qualitative results further confirm that PaIR-Drive can effectively explore and generate high-quality trajectories.
  •  
  • ↗️
↗️

Advances in Metabolic Reprogramming and Immune Regulatory Mechanisms in Lung Cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Xiaomeng Li · Xuejiao Li · Hongbo Wu · Rui Li

Oncol Res. 2026 Mar 23;34(4):11. doi: 10.32604/or.2026.076176. eCollection 2026.

ABSTRACT

Lung cancer remains the leading cause of cancer-related mortality worldwide, primarily driven by metabolic reprogramming and immune evasion mechanisms within tumor cells. To adapt to the nutrient-deprived tumor microenvironment (TME), lung cancer cells undergo profound metabolic reprogramming, characterized by enhanced glycolysis (the Warburg effect), increased glutamine dependency (mediated by GLS1), and accelerated lipid synthesis (involving enzymes such as FASN). These metabolic alterations not only remodel the TME but also dampen antitumor immune responses by promoting immunosuppressive cell populations (e.g., Tregs and M2 macrophages) and inhibiting effector functions of CD8+ T cells and natural killer (NK) cells. Critically, a bidirectional crosstalk operates between tumor cell metabolism and the immunosuppressive TME: metabolic reprogramming drives immune suppression through metabolite accumulation, whereas the immunosuppressive TME, in turn, promotes tumor cell adaptability-thus forming a positive feedback loop that reinforces immune evasion and therapy resistance. This review elucidates key molecular pathways governing metabolic reprogramming in lung cancer-spanning glucose, amino acid, and lipid metabolism-and their dynamic crosstalk with immune regulation, including epigenetic modifications and non-coding RNA-mediated mechanisms. Additionally, it evaluates emerging therapeutic strategies targeting the metabolic-immune axis, such as inhibitors of HK2 or GLS1 combined with anti-PD-1/PD-L1 agents, which aim to reverse immunosuppression and improve clinical outcomes. By synthesizing recent advances, this work provides a theoretical framework for precision oncology interventions, highlighting the potential of metabolic immunotherapies and future directions integrating AI and multi-omics data to overcome resistance in lung cancer.

PMID:41930159 | PMC:PMC13040304 | DOI:10.32604/or.2026.076176

  •  
  • ↗️
↗️

Advances in Metabolic Reprogramming and Immune Regulatory Mechanisms in Lung Cancer

✇Omics In Lung
By: Xiaomeng Li · Xuejiao Li · Hongbo Wu · Rui Li

Oncol Res. 2026 Mar 23;34(4):11. doi: 10.32604/or.2026.076176. eCollection 2026.

ABSTRACT

Lung cancer remains the leading cause of cancer-related mortality worldwide, primarily driven by metabolic reprogramming and immune evasion mechanisms within tumor cells. To adapt to the nutrient-deprived tumor microenvironment (TME), lung cancer cells undergo profound metabolic reprogramming, characterized by enhanced glycolysis (the Warburg effect), increased glutamine dependency (mediated by GLS1), and accelerated lipid synthesis (involving enzymes such as FASN). These metabolic alterations not only remodel the TME but also dampen antitumor immune responses by promoting immunosuppressive cell populations (e.g., Tregs and M2 macrophages) and inhibiting effector functions of CD8+ T cells and natural killer (NK) cells. Critically, a bidirectional crosstalk operates between tumor cell metabolism and the immunosuppressive TME: metabolic reprogramming drives immune suppression through metabolite accumulation, whereas the immunosuppressive TME, in turn, promotes tumor cell adaptability-thus forming a positive feedback loop that reinforces immune evasion and therapy resistance. This review elucidates key molecular pathways governing metabolic reprogramming in lung cancer-spanning glucose, amino acid, and lipid metabolism-and their dynamic crosstalk with immune regulation, including epigenetic modifications and non-coding RNA-mediated mechanisms. Additionally, it evaluates emerging therapeutic strategies targeting the metabolic-immune axis, such as inhibitors of HK2 or GLS1 combined with anti-PD-1/PD-L1 agents, which aim to reverse immunosuppression and improve clinical outcomes. By synthesizing recent advances, this work provides a theoretical framework for precision oncology interventions, highlighting the potential of metabolic immunotherapies and future directions integrating AI and multi-omics data to overcome resistance in lung cancer.

PMID:41930159 | PMC:PMC13040304 | DOI:10.32604/or.2026.076176

  •  
  • ↗️
↗️

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Han Wang · Yifan Sun · Brian Ko · Mann Talati · Jiawen Gong · Zimeng Li · Naicheng Yu · Xucheng Yu · Wei Shen · Vedant Jolly · Huan Zhang
arXiv:2603.28590v2 Announce Type: replace Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize \textit{when} CoTs can be used to monitor the factors driving LLM behavior; and (2) two stress-test settings to quantify \textit{the extent to which} CoT monitorability can be degraded. Extensive experiments across multiple popular LLMs with varying capabilities show that CoT monitorability is higher when the decision-critical factors shape the intermediate reasoning process without merely influencing the final answer. More capable LLMs tend to exhibit lower monitorability. And all evaluated LLMs can intentionally reduce monitorability under stress-tests, with monitorability dropping by up to 30\% in some tasks that do not require structural reasoning over the decision-critical factors. Overall, MonitorBench provides a basis for further research on evaluating future LLMs, studying advanced stress-test monitorability techniques, and developing new monitoring approaches. The code is available at https://github.com/ASTRAL-Group/MonitorBench.
  •  
  • ↗️
↗️

PRET is a few-shot system for pan-cancer recognition without example training

✇Nature Cancer
By: Yi Li · Ziyu Ning · Tianqi Xiang · Qixiang Zhang · Zhihao Lin · Min Yi · Feiyan Feng · Baozhen Zeng · Xuexia Qian · Lu Sun · Jiace Qin · Ling Xiang · Chao Fan · Tian Qin · Qian Wang · Xiu-Wu Bian · Kun-Hsing Yu · Kang Zhang · Qingling Zhang · Xiaomeng Li

Nature Cancer, Published online: 03 April 2026; doi:10.1038/s43018-026-01141-2

Li et al. present PRET, a few-shot system for pan-cancer detection not requiring model fine-tuning, validated it in multicenter datasets and found that it outperformed existing approaches across tasks and pathologists in lymph node metastasis detection.
  •  
  • ↗️
↗️

VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Juan Rodriguez · Haotian Zhang · Abhay Puri · Tianyang Zhang · Rishav Pramanik · Meng Lin · Xiaoqing Xie · Marco Terral · Darsh Kaushik · Aly Shariff · Perouz Taslakian · Spandana Gella · Sai Rajeswar · David Vazquez · Christopher Pal · Marco Pedersoli
arXiv:2603.29852v1 Announce Type: cross Abstract: We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding. VectorGym addresses the lack of realistic, challenging benchmarks aligned with professional design workflows. Our benchmark comprises four tasks with expert human-authored annotations: the novel Sketch2SVG task (VG-Sketch); a new SVG editing dataset (VG-Edit) featuring complex, multi-step edits with higher-order primitives; Text2SVG generation (VG-Text); and SVG captioning (VG-Cap). Unlike prior benchmarks that rely on synthetic edits, VectorGym provides gold-standard human annotations that require semantic understanding and design intent. We also propose a multi-task reinforcement learning approach that jointly optimizes across all four tasks using rendering-based rewards. Our method, built on GRPO with curriculum learning, trains a Qwen3-VL 8B model that achieves state-of-the-art performance among open-source models, surpassing much larger models including Qwen3-VL 235B and matching GPT-4o. We also introduce a VLM-as-a-Judge metric for SVG generation, validated through human correlation studies. Our evaluation of frontier VLMs reveals significant performance gaps, positioning VectorGym as a rigorous framework for advancing visual code generation. VectorGym is publicly available on huggingface.co/datasets/ServiceNow/VectorGym.
  •  
  • ↗️
↗️

Hijacking ERAD for targeted degradation of transmembrane proteins

✇Cell
By: Haikun Song · Wei Wang · Tingfang Mei · Huiwen Zheng · Keni Ning · Xiaofan Liu · Siulam Cheung · Zhiyuan Cao · Danqi Sheng · Xiaohan Mai · Haoran Zhu · Guankai Guo · Shuaimeng Liu · Rongkai Wei · Qian Wang · Yu Cao · Yu Ding · Yiyan Fei · Rui Liu · Motoyuki Hattori · Chunquan Sheng · Boxun Lu
Development of an ERAD-hijacking technology overcomes the challenges of current targeted protein degradation approaches to achieve degradation of transmembrane proteins.
  •  
  • ↗️
↗️

Towards unified brain-to-text decoding across speech production and perception

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhizhang Yuan · Yang Yang · Gaorui Zhang · Baowen Cheng · Zehan Wu · Yuhao Xu · Xiaoying Liu · Liang Chen · Ying Mao · Meng Li
arXiv:2603.12628v1 Announce Type: new Abstract: Speech production and perception are the main ways humans communicate daily. Prior brain-to-text decoding studies have largely focused on a single modality and alphabetic languages. Here, we present a unified brain-to-sentence decoding framework for both speech production and perception in Mandarin Chinese. The framework exhibits strong generalization ability, enabling sentence-level decoding when trained only on single-character data and supporting characters and syllables unseen during training. In addition, it allows direct and controlled comparison of neural dynamics across modalities. Mandarin speech is decoded by first classifying syllable components in Hanyu Pinyin, namely initials and finals, from neural signals, followed by a post-trained large language model (LLM) that maps sequences of toneless Pinyin syllables to Chinese sentences. To enhance LLM decoding, we designed a three-stage post-training and two-stage inference framework based on a 7-billion-parameter LLM, achieving overall performance that exceeds larger commercial LLMs with hundreds of billions of parameters or more. In addition, several characteristics were observed in Mandarin speech production and perception: speech production involved neural responses across broader cortical regions than auditory perception; channels responsive to both modalities exhibited similar activity patterns, with speech perception showing a temporal delay relative to production; and decoding performance was broadly comparable across hemispheres. Our work not only establishes the feasibility of a unified decoding framework but also provides insights into the neural characteristics of Mandarin speech production and perception. These advances contribute to brain-to-text decoding in logosyllabic languages and pave the way toward neural language decoding systems supporting multiple modalities.
  •  
  • ↗️
↗️

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinwu Ye · Yicheng Mao · Jia Zhang · Yimeng Liu · Li Hao · Fang Wu · Zhiwei Li · Yuxuan Liao · Zehong Wang · Yingcheng Wu · Zhiyuan Liu · Zhenfei Yin · Li Yuan · Philip Torr · Huan Sun · Xiangxiang Zeng · Mengdi Wang · Le Cong · Shenghua Gao · Xiangru Tang
arXiv:2602.07075v4 Announce Type: replace-cross Abstract: Chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) in natural language to perform complex reasoning. However, chemical reasoning is inherently continuous and structural, and forcing it into discrete linguistic tokens introduces a fundamental representation mismatch that constrains both efficiency and performance. We introduce LatentChem, a latent reasoning interface that decouples chemical computation from textual generation, enabling models to perform multi-step reasoning directly in continuous latent space while emitting language only for final outputs. Remarkably, we observe a consistent emergent behavior: when optimized solely for task success, models spontaneously internalize reasoning, progressively abandoning verbose textual derivations in favor of implicit latent computation. This shift is not merely stylistic but computationally advantageous. Across diverse chemical reasoning benchmarks, LatentChem achieves a 59.88\% non-tie win rate over strong CoT-based baselines on ChemCoTBench, while delivering a 10.84$\times$ average reduction in reasoning overhead. Our results provide empirical evidence that chemical reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.
  •  
  • ↗️
↗️

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song
arXiv:2602.07801v3 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.
  •  
  • ↗️
↗️

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuchen Wang · Haonan Wang · Yu Guo · Honglong Yang · Xiaomeng Li
arXiv:2603.03312v1 Announce Type: cross Abstract: Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental limitations: Semantic Bias (mode collapse into generic templates), Signal Neglect (hallucination based on linguistic priors rather than neural inputs), and the BLEU Trap, where evaluation metrics are artificially inflated by high-frequency stopwords, masking a lack of true semantic fidelity. To address these challenges, we propose SemKey, a novel multi-stage framework that enforces signal-grounded generation through four decoupled semantic objectives: sentiment, topic, length, and surprisal. We redesign the interaction between the neural encoder and the Large Language Model (LLM) by injecting semantic prompts as Queries and EEG embeddings as Key-Value pairs, strictly forcing the model to attend to neural inputs. Furthermore, we move beyond standard translation metrics by adopting N-way Retrieval Accuracy and Fr\'echet Distance to rigorously assess diversity and alignment. Extensive experiments demonstrate that our approach effectively eliminates hallucinations on noise inputs and achieves SOTA performance on these robust protocols. Code will be released upon acceptance at https://github.com/xmed-lab/SemKey.
  •  
  • ↗️
↗️

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenqi Liu · Yunxiao Wang · Shijie Ma · Meng Liu · Qile Su · Tianke Zhang · Haonan Fan · Changyi Liu · Kaiyu Jiang · Jiankang Chen · Kaiyu Tang · Bin Wen · Fan Yang · Tingting Gao · Han Li · Yinwei Wei · Xuemeng Song
arXiv:2602.07801v2 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize-clip-answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.
  •  
  • ↗️
↗️

UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenxuan Zeng · Chao Yang · Tianshi Xu · Bo Zhang · Changrui Ren · Jin Dong · Meng Li
arXiv:2602.18758v1 Announce Type: cross Abstract: Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC inference framework that jointly optimizes the 2PC protocols and quantization algorithm. UFO features a novel 2PC protocol that systematically combines the efficient Winograd convolution algorithm with quantization to improve inference efficiency. However, we observe that naively combining quantization and Winograd convolution faces the following challenges: 1) From the inference perspective, Winograd transformations introduce extensive additions and require frequent bit width conversions to avoid inference overflow, leading to non-negligible communication overhead; 2) From the training perspective, Winograd transformations introduce weight outliers that make quantization-aware training (QAT) difficult, resulting in inferior model accuracy. To address these challenges, we co-optimize both protocol and algorithm. 1) At the protocol level, we propose a series of graph-level optimizations for 2PC inference to minimize the communication. 2) At the algorithm level, we develop a mixed-precision QAT algorithm based on layer sensitivity to optimize model accuracy given communication constraints. To accommodate the outliers, we further introduce a 2PC-friendly bit re-weighting algorithm to increase the representation range without explicitly increasing bit widths. With extensive experiments, UFO demonstrates 11.7x, 3.6x, and 6.3x communication reduction with 1.29%, 1.16%, and 1.29% higher accuracy compared to state-of-the-art frameworks SiRNN, COINN, and CoPriv, respectively.
  •  
  • ↗️
↗️

DenseMLLM: Standard Multimodal LLMs are Intrinsic Dense Predictors

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Li · Hongze Shen · Lexiang Tang · Xin Li · Xinpeng Ding · Yinsong Liu · Deqiang Jiang · Xing Sun · Xiaomeng Li
arXiv:2602.14134v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending these models to fine-grained dense prediction tasks, such as semantic segmentation and depth estimation, typically necessitates the incorporation of complex, task-specific decoders and other customizations. This architectural fragmentation increases model complexity and deviates from the generalist design of MLLMs, ultimately limiting their practicality. In this work, we challenge this paradigm by accommodating standard MLLMs to perform dense predictions without requiring additional task-specific decoders. The proposed model is called DenseMLLM, grounded in the standard architecture with a novel vision token supervision strategy for multiple labels and tasks. Despite its minimalist design, our model achieves highly competitive performance across a wide range of dense prediction and vision-language benchmarks, demonstrating that a standard, general-purpose MLLM can effectively support dense perception without architectural specialization.
  •  
  • ↗️
There are no more articles
❌