RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

By: Haichuan Hu · Yang Xiao · Mingni Tang · Jiawen Duan · Quanjun Zhang · Congqing He · Hao Zhang · Jiashuo Wang · Johan F. Hoorn · Wenjie Li

10 September 2026 at 12:00

arXiv:2609.09657v1 Announce Type: new Abstract: Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual emotional states, leaving interpersonal relations in multi-party scenarios underexplored. In this work, we introduce relation-aware emotional support conversation, a new task that evaluates whether LLMs can capture and utilize the evolving dynamics of relationships to offer more effective emotional support. We construct RESCUE (Relation-aware Emotional Support Conversation Understanding and Evaluation Benchmark) from real couple and family interview conversations, containing 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video. Based on rich annotations of socio-emotional and support-related dynamics, RESCUE defines six tasks that evaluate two core capabilities required for relation-aware emotional support: Relational Understanding and Relation-Sensitive Support. Experiments with ten LLMs show that current models perform relatively well on tasks relying on local emotional or intervention cues, but struggle with relation-intensive tasks such as relation pattern prediction, viewpoint prediction, and support strategy prediction. These findings reveal the limitations of current LLMs in modeling interpersonal relations and making relation-sensitive support decisions.

A Non-Canonical Role of SMAD4 in Regulating 3D Genome Architecture to Inhibit Lung Squamous Cell Carcinoma Development

(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)

By: Qian Tang · Chen Lian · Xinyan Han · Xuhan Zhang · Zihan Wang · Boyu Wang · Taoyu Zhu · Xinrui Lin · Xiaolei Wang · Yaping Xu · Manyu Xiao · Zijin Wang · Junming Li · Silin Chen · Yunze Wang · Yufei Liu · Songsong Li · Zuolin Shen · Xi Lu · Xueqi Han · Yilu Zhou · Mingyang Xiao · Jiayi Ran · Xiaoran Cao · Xinyi Xu · Hugo Sámano-Sánchez · Alfredo Rodríguez · Lian Wang · Shuifang Chen · Zhanyu Xu · Shirong Zhang · Nuo Yang · Yong Tang · Jian Liu

26 May 2026 at 18:00

Adv Sci (Weinh). 2026 May 26:e75839. doi: 10.1002/advs.75839. Online ahead of print.

ABSTRACT

Lung squamous cell carcinoma (LUSC) lacks clearly defined key drivers and effective targeted therapies, reflecting an incomplete understanding of its molecular pathogenesis. Here, we identify SMAD4 as a critical regulator of three-dimensional (3D) genome organization in LUSC and uncover a mechanistic link between tumor suppressor loss and oncogenic transcriptional activation. By integrating clinical datasets, genetically engineered mouse models, human and murine LUSC cell lines, and multi-omics analyses, we demonstrate that SMAD4 deficiency promotes LUSC progression by unleashing EP300-mediated enhancer-promoter looping at the SOX2 locus. Mechanistically, SMAD4 does not directly bind SOX2 regulatory elements but instead constrains chromatin looping by sequestering EP300 away from loop anchor regions. Loss of SMAD4 leads to enhanced H3K27ac deposition, aberrant SOX2 activation, and increased LUSC tumor cell proliferation. Together, these findings reveal a non-canonical role for a transcription factor (e.g., SMAD4) in regulating dysregulated 3D genome architecture to inhibit tumor development.

PMID:42189071 | DOI:10.1002/advs.75839

A Non-Canonical Role of SMAD4 in Regulating 3D Genome Architecture to Inhibit Lung Squamous Cell Carcinoma Development

Omics In Lung

By: Qian Tang · Chen Lian · Xinyan Han · Xuhan Zhang · Zihan Wang · Boyu Wang · Taoyu Zhu · Xinrui Lin · Xiaolei Wang · Yaping Xu · Manyu Xiao · Zijin Wang · Junming Li · Silin Chen · Yunze Wang · Yufei Liu · Songsong Li · Zuolin Shen · Xi Lu · Xueqi Han · Yilu Zhou · Mingyang Xiao · Jiayi Ran · Xiaoran Cao · Xinyi Xu · Hugo Sámano-Sánchez · Alfredo Rodríguez · Lian Wang · Shuifang Chen · Zhanyu Xu · Shirong Zhang · Nuo Yang · Yong Tang · Jian Liu

26 May 2026 at 18:00

Adv Sci (Weinh). 2026 May 26:e75839. doi: 10.1002/advs.75839. Online ahead of print.

ABSTRACT

Lung squamous cell carcinoma (LUSC) lacks clearly defined key drivers and effective targeted therapies, reflecting an incomplete understanding of its molecular pathogenesis. Here, we identify SMAD4 as a critical regulator of three-dimensional (3D) genome organization in LUSC and uncover a mechanistic link between tumor suppressor loss and oncogenic transcriptional activation. By integrating clinical datasets, genetically engineered mouse models, human and murine LUSC cell lines, and multi-omics analyses, we demonstrate that SMAD4 deficiency promotes LUSC progression by unleashing EP300-mediated enhancer-promoter looping at the SOX2 locus. Mechanistically, SMAD4 does not directly bind SOX2 regulatory elements but instead constrains chromatin looping by sequestering EP300 away from loop anchor regions. Loss of SMAD4 leads to enhanced H3K27ac deposition, aberrant SOX2 activation, and increased LUSC tumor cell proliferation. Together, these findings reveal a non-canonical role for a transcription factor (e.g., SMAD4) in regulating dysregulated 3D genome architecture to inhibit tumor development.

PMID:42189071 | DOI:10.1002/advs.75839

Rethinking Federated Unlearning via the Lens of Memorization

cs.AI, q-bio.NC updates on arXiv.org

By: Jiaheng Wei · Yanjun Zhang · He Zhang · Leo Yu Zhang · Chao Chen · Kok-Leong Ong · Jun Zhang · Yang Xiang

26 May 2026 at 12:00

arXiv:2605.24545v1 Announce Type: cross Abstract: Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and remaining data, leading to ineffective unlearning and unfairness between clients. In this work, we revisit federated unlearning through the lens of memorization. We argue that unlearning should mainly remove the unique memorized information attributable to the data to be forgotten, while preserving overlapping patterns that are also supported by the remaining data. Specifically, we propose Grouped Memorization Evaluation, an example-level metric that separates memorized knowledge from overlapping knowledge. Building on this metric, we introduce Federated Memorization Pruning (FedMemPrune), a pruning-based unlearning approach that resets redundant parameters responsible for memorization. Extensive experiments show that FedMemPrune closely matches retraining-based unlearning baselines while more effectively eliminating memorization than existing federated unlearning algorithms, yielding strong unlearning performance without sacrificing the utility of retained knowledge.

OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization

cs.AI, q-bio.NC updates on arXiv.org

By: Maoyang Xiang · Bo Wang · Tao Luo

26 May 2026 at 12:00

arXiv:2605.26092v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays. In the ultra-low bit regime, logarithmic Power-of-Two (PoT) quantization provides a hardware-efficient alternative by replacing MAC operations with bit-shifts. However, the non-uniform exponential lattice is inherently limited by a \textbf{Low Angular Resolution Regime}, a structural flaw that becomes particularly pronounced at sub-4-bit thresholds, leading to a notable degradation of high-dimensional feature manifolds. To address this geometric limitation, we propose Orthogonal Residual Projection (ORP), an algorithm-hardware co-design framework. By formulating quantization as a dual-basis geometric projection, ORP adaptively synthesizes a higher-resolution residual lattice using strictly shift-and-add operations. Furthermore, ORP's analytical solver offers a practical alternative to computationally intensive gradient-based optimization, reducing the full-model calibration time for LLaMA-2-7B to approximately \textbf{15 minutes}. Extensive evaluations demonstrate ORP's applicability across modalities and its hardware efficiency. Under the 3-bit (W3/A16) constraint, ORP achieves a perplexity of 6.10 on LLaMA-2-7B, comparing favorably to conventional MAC-intensive baselines like AWQ without relying on asymmetric scaling, while maintaining competitive accuracy in 4-bit scenarios. At the silicon level, standard-cell RTL synthesis at a 28nm node indicates that ORP effectively mitigates the timing bottlenecks associated with dense multiplier trees.

Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System

cs.AI, q-bio.NC updates on arXiv.org

By: Longfei Yun · Yihan Wu · Haoran Liu · Xiaoxuan Liu · Ziyun Xu · Yi Wang · Yang Xia · Pengfei Wang · Mingze Gao · Yunxiang Wang · Changfan Chen · Wenjie Fu · Hong Yan · Junfeng Pan

26 May 2026 at 12:00

arXiv:2602.18640v2 Announce Type: replace Abstract: Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context constraint: the arduous process of translating ambiguous product intent into reasonable, executable, verifiable hypotheses, rather than by modeling techniques alone. We present GEARS (Generative Engine for Agentic Ranking Systems), a framework that reframes ranking optimization as an autonomous discovery process within a programmable experimentation environment. Rather than treating optimization as static model selection, GEARS leverages Specialized Agent Skills to encapsulate ranking expert knowledge into reusable reasoning capabilities, enabling operators to steer systems via high-level intent vibe personalization. Furthermore, to ensure production reliability, the framework incorporates validation hooks to enforce statistical robustness and filter out brittle policies that overfit short-term signals. Experimental validation across diverse product surfaces demonstrates that GEARS consistently identifies superior, near-Pareto-efficient policies by synergizing algorithmic signals with deep ranking context while maintaining rigorous deployment stability.

Androgen activity in the male embryonic hindbrain drives lethal PFA ependymoma

Nature - Issue - nature.com science feeds

By: Jiao Zhang · Winnie Ong · Alexandra Rasnitsyn · Ricardo Daniel Gonzalez · Rodrigo Lopez Gutierrez · Polina Balin · Amr Saadeldin · Xiaochong Wu · Maria C. Vladoiu · Vicente Santa-Maria Lopez · Fernando Gonzalez-Salinas · Navneesh Yadav · Dinesh Mohanakrishnan · Kannan Boosi Narayana Rao · Raja Gopal Reddy Mooli · Hinda Najem · Sebastian Pacheco · Kaitlin Kharas · Cory Richman · David Przelicki · Evan Y. Wang · Haipeng Su · Rachel Naomi Curry · Runze Yang · Michelle Masayo Kameda-Smith · Bryn Livingston · David Scott · Zaili Luo · Mingyang Xia · Namal Abeysundara · Anders W. Erickson · Ncedile Mankahla · Lucas ZhongMing Hu · Chu Pan · Raul Suarez · Ning Huang · Yihao Wu · Hao Wang · Tajana Douglas · Jonelle Pallota · Steven Hébert · Karen Ng · Krystin Mantione · Heather Whetstone · Hassaan Maan · Hussein Lakkis · Juyeun Lee · Sadeesh K. Ramakrishnan · Yanxin Pei · Yujie Tang · Frank Y. Lin · Guillermo Aldave · Marco Gallo · Robert M. Friedlander · Faiyaz Notta · Laura K. Donovan · Murali Chintagumpala · Bo Wang · Yun Li · Daniel D. De Carvalho · Zhaolei Zhang · Ying M

25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10264-6

Androgen activity in the male embryonic hindbrain prolongs hindbrain differentiation in male individuals and drives sex differences in the incidence and prognosis of posterior fossa type A (PFA) ependymoma, an aggressive childhood brain tumour.

Stabilizing Reinforcement Learning for Diffusion Language Models

cs.AI, q-bio.NC updates on arXiv.org

By: Jianyuan Zhong · Kaibo Wang · Ding Ding · Zijin Feng · Haoli Bai · Yang Xiang · Jiacheng Sun · Qiang Xu

10 March 2026 at 12:00

arXiv:2603.06743v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two sources of incompatibility. First, GRPO relies on importance ratios defined by sequence probabilities, which are intractable in dLLMs and must be estimated (e.g., via ELBO-based or mean-field likelihood proxies), yielding inherently noisy ratios. Second, standard GRPO's formulation is not designed for estimated ratios: its conditional clipping can be anomalously bypassed by model-agnostic estimation noise, producing gradient spikes, while its fixed group-size normalization amplifies gradient-magnitude fluctuations under high-variance ratio estimates. We show these effects form a self-reinforcing instability loop that drives policy drift and further increases ratio variance. To break this loop, we propose StableDRL, a reformulation of GRPO tailored for dLLMs that uses (i) unconditional clipping to suppress outlier-induced spikes and (ii) self-normalization to constrain updates within the convex hull of per-sample gradients. We further extend StableDRL to block-wise diffusion models via a staircase attention mechanism.

UnfoldLDM: Deep Unfolding-based Blind Image Restoration with Latent Diffusion Priors

cs.AI, q-bio.NC updates on arXiv.org

By: Chunming He · Rihan Zhang · Zheng Chen · Bowen Yang · Chengyu Fang · Yunlong Lin · Yulun Zhang · Fengyang Xiao · Sina Farsiu

10 March 2026 at 12:00

arXiv:2511.18152v2 Announce Type: replace-cross Abstract: Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited for blind image restoration (BIR). Existing DUNs suffer from: (1) \textbf{Degradation-specific dependency}, as their optimization frameworks are tied to a known degradation model, making them unsuitable for BIR tasks; and (2) \textbf{Over-smoothing bias}, resulting from the direct feeding of gradient descent outputs, dominated by low-frequency content, into the proximal term, suppressing fine textures. To overcome these issues, we propose UnfoldLDM to integrate DUNs with latent diffusion model (LDM) for BIR. In each stage, UnfoldLDM employs a multi-granularity degradation-aware (MGDA) module as the gradient descent step. MGDA models BIR as an unknown degradation estimation problem and estimates both the holistic degradation matrix and its decomposed forms, enabling robust degradation removal. For the proximal step, we design a degradation-resistant LDM (DR-LDM) to extract compact degradation-invariant priors from the MGDA output. Guided by this prior, an over-smoothing correction transformer (OCFormer) explicitly recovers high-frequency components and enhances texture details. This unique combination ensures the final result is degradation-free and visually rich. Experiments show that our UnfoldLDM achieves a leading place on various BIR tasks and benefits downstream tasks. Moreover, our design is compatible with existing DUN-based methods, serving as a plug-and-play framework. Code will be released.

Delegation and Verification Under AI

cs.AI, q-bio.NC updates on arXiv.org

By: Lingxiao Huang · Wenyang Xiao · Nisheeth K. Vishnoi

4 March 2026 at 13:00

arXiv:2603.02961v1 Announce Type: cross Abstract: As AI systems enter institutional workflows, workers must decide whether to delegate task execution to AI and how much effort to invest in verifying AI outputs, while institutions evaluate workers using outcome-based standards that may misalign with workers' private costs. We model delegation and verification as the solution to a rational worker's optimization problem, and define worker quality by evaluating an institution-centered utility (distinct from the worker's objective) at the resulting optimal action. We formally characterize optimal worker workflows and show that AI induces *phase transitions*, where arbitrarily small differences in verification ability lead to sharply different behaviors. As a result, AI can amplify workers with strong verification reliability while degrading institutional worker quality for others who rationally over-delegate and reduce oversight, even when baseline task success improves and no behavioral biases are present. These results identify a structural mechanism by which AI reshapes institutional worker quality and amplifies quality disparities between workers with different verification reliability.

Hot-Start from Pixels: Low-Resolution Visual Tokens for Chinese Language Modeling

cs.AI, q-bio.NC updates on arXiv.org

By: Shuyang Xiang · Hao Guan

4 March 2026 at 13:00

arXiv:2601.09566v3 Announce Type: replace-cross Abstract: Large language models typically represent Chinese characters as discrete index-based tokens, largely ignoring their visual form. For logographic scripts, visual structure carries semantic and phonetic information, which may aid prediction. We investigate whether low-resolution visual inputs can serve as an alternative for character-level modeling. Instead of token IDs, our decoder receives grayscale images of individual characters, with resolutions as low as 8 x 8 pixels. Remarkably, these inputs achieve 39.2% accuracy, comparable to the index-based baseline of 39.1%. Such low-resource settings also exhibit a pronounced hot-start effect: by 0.4% of total training, accuracy reaches above 12%, while index-based models lag at below 6%. Overall, our results demonstrate that minimal visual structure can provide a robust and efficient signal for Chinese language modeling, offering an alternative perspective on character representation that complements traditional index-based approaches.

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

cs.AI, q-bio.NC updates on arXiv.org

By: Cong Wang · Changfeng Gao · Yang Xiang · Zhihao Du · Keyu An · Han Zhao · Qian Chen · Xiangang Li · Yingming Gao · Ya Li

17 February 2026 at 13:00

arXiv:2512.04552v3 Announce Type: replace-cross Abstract: Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acoustic artifacts to achieve spurious rewards, but at the cost of degrading perceptual quality. To address this, we propose Robust Reward Policy Optimization (RRPO), a novel framework that employs a hybrid regularization scheme. This scheme develops a robust RM whose reward signal is more reliably aligned with human perception, compelling the policy to abandon detrimental shortcuts and instead learn the complex features of genuine emotions. Our ablation study confirms the enhanced robustness of our RM, as evidenced by its strong cross-lingual generalization. The subjective evaluation demonstrates that this robust RM effectively mitigates reward hacking, leading to significant improvements in both emotional expressiveness and naturalness over all baselines. Demo page: https://lrwinr.github.io/RRPO-CosyVoice.

Reading view