❌

Normal view

Received — 10 September 2026 ⏭

PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuchen Sun · Qian Yang · Jun Wang · Detai Xin · Guoqiao Yu · Guanglu Wan · Qi Jia
10 September 2026 at 12:00
arXiv:2609.04867v2 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either treat audio as an auxiliary component of video quality or assess it in isolation from audiovisual grounding, making it difficult to diagnose where current systems truly succeed or fail in audio generation. We present PRISM-Bench, the first audio-centric diagnostic benchmark for T2AV generation. Built from a rigorously curated dataset of 900 human-verified samples, PRISM-Bench factorizes audio evaluation along two orthogonal axes: audio type (Speech, Music, and Sound) and sound-source visibility (On-screen vs. Off-screen). It evaluates generated content across four perceptual dimensions (Audio-Visual Coherence, Audio Quality, Audio Expressiveness, and Prompt Following) with 35 fine-grained criteria. To ensure reliable assessment, we adopt an enhanced MLLM-as-a-Judge protocol based on blind, side-by-side comparison against ground-truth references, demonstrating strong alignment (over 70% mean agreement) with human raters. Our evaluation of recent T2AV systems highlights a significant performance gap between frontier and open-source models. Furthermore, we demonstrate that current generation paradigms overfit to perceptual fidelity while struggling with complex grounding and control tasks, particularly in generating music and synchronized On-screen audio.
Received — 8 April 2026 ⏭

Discovering Failure Modes in Vision-Language Models using RL

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kanishk Jain · Qian Yang · Shravan Nayak · Parisa Kordjamshidi · Nishanth Anand · Aishwarya Agrawal
7 April 2026 at 12:00
arXiv:2604.04733v1 Announce Type: cross Abstract: Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint understanding. Previous studies manually identified these weaknesses and found that they often stem from deficits in specific skills. However, such manual efforts are costly, unscalable, and subject to human bias, which often overlooks subtle details in favor of salient objects, resulting in an incomplete understanding of a model's vulnerabilities. To address these limitations, we propose a Reinforcement Learning (RL)-based framework to automatically discover the failure modes or blind spots of any candidate VLM on a given data distribution without human intervention. Our framework trains a questioner agent that adaptively generates queries based on the candidate VLM's responses to elicit incorrect answers. Our approach increases question complexity by focusing on fine-grained visual details and distinct skill compositions as training progresses, consequently identifying 36 novel failure modes in which VLMs struggle. We demonstrate the broad applicability of our framework by showcasing its generalizability across various model combinations.
Received — 2 April 2026 ⏭

Dynamic Targetable Extracellular Vesicle Surface Proteins Monitor Depth of Response to CAR T Therapy

✇MRD
By: Chen Zhao · Lei Qiu · Ning An · Yong Ju · Jacqueline Ziqian Yang · Hyoyong Kim · Ryan Y Zhang · Junseok Lee · Jingjing He · Liang-Yan Chen · Yaya Xu · Yue Ma · Emily Ren · Sophie Pan · Pranay Sashikanth · Jina Kim · Di Wang · Peiling Zhang · Jianlin Hu · Yang Gao · Yuhan Bao · Yanhua Tu · Li Wang · Zhili Wang · Zhicheng Zhang · Renjun Pei · Edwin M Posadas · Sungyong You · Wanxing Chai-Ho · Tasha L Lin · Sarah M Larson · Dinesh S Rao · Hsian-Rong Tseng · Na Sun · Chunrui Li · Yazhen Zhu
27 March 2026 at 18:00

Res Sq [Preprint]. 2026 Mar 18:rs.3.rs-8913641. doi: 10.21203/rs.3.rs-8913641/v1.

ABSTRACT

Extracellular vesicles (EVs) represent a promising liquid biopsy platform in multiple myeloma (MM). We developed an MM EV Surface Protein Assay to quantify and dynamically monitor four MM EV subpopulations defined by targetable MM surface proteins (BCMA, CD38, GPRC5D, and CD319) across 336 serial blood samples from 45 relapsed/refractory MM (RRMM) patients treated with anti-BCMA chimeric antigen receptor (CAR) T-cell therapy. All four MM EV subpopulations significantly decreased in 43 patients with initial response, while BCMA+, GPRC5D+, and CD319+ MM EVs increased in 19 patients with progression, and antigen escape was detected by BCMA+ MM EVs. MM EV subpopulations differentiated minimal residual disease (MRD) status and complemented MRD for detecting early relapse before clinical progression. Notably, CD319+ MM EVs were early predictors of progression-free and overall survival in MRD-negative patients. This assay enables noninvasive monitoring of deep response, progression, and antigen escape, and stratifies survival in MRD-negative patients with RRMM.

PMID:41890853 | PMC:PMC13015583 | DOI:10.21203/rs.3.rs-8913641/v1

Received — 26 March 2026 ⏭

Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xun Huang · Simeng Qin · Xiaoshuang Jia · Ranjie Duan · Huanqian Yan · Zhitao Zeng · Fei Yang · Yang Liu · Xiaojun Jia
25 March 2026 at 12:00
arXiv:2602.22983v3 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak attacks, with effectiveness varying across language contexts. This paper investigates the role of classical Chinese in jailbreak attacks. Owing to its conciseness and obscurity, classical Chinese can partially bypass existing safety constraints, exposing notable vulnerabilities in LLMs. Based on this observation, this paper proposes a framework, CC-BOS, for the automatic generation of classical Chinese adversarial prompts based on multi-dimensional fruit fly optimization, facilitating efficient and automated jailbreak attacks in black-box settings. Prompts are encoded into eight policy dimensions-covering role, behavior, mechanism, metaphor, expression, knowledge, trigger pattern and context; and iteratively refined via smell search, visual search, and cauchy mutation. This design enables efficient exploration of the search space, thereby enhancing the effectiveness of black-box jailbreak attacks. To enhance readability and evaluation accuracy, we further design a classical Chinese to English translation module. Extensive experiments demonstrate that effectiveness of the proposed CC-BOS, consistently outperforming state-of-the-art jailbreak attack methods.

RFC4 drives temozolomide resistance in glioblastoma by activating STK38-BECN1-dependent autophagy

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Min Mao · Hang Ji · Wen-Qian Yu · Qu-Jing Gai · Qiang Sun · Qian Yan · Sen-Lin Xu · Meng-Li Zhu · Mei-Hua Qu · Han-Min Liu · Jean-Philipe Hugnot · Xi He · Xin Wang · Yan Wang
24 March 2026 at 18:00

Nat Commun. 2026 Mar 23. doi: 10.1038/s41467-026-70798-1. Online ahead of print.

ABSTRACT

Glioblastoma (GBM) remains a lethal brain tumor due to therapy resistance. While autophagy contributes to temozolomide (TMZ) resistance, its regulation is incompletely understood. This study investigates the role of replication factor RFC4, which is associated with poor prognosis and TMZ resistance in GBM. Multi-omics analyses and molecular experiments reveal that TMZ-induced chromatin accessibility enables transcription factor YY1 to bind the RFC4 promoter and upregulate its expression. RFC4, in turn, stabilizes the kinase STK38, which is essential for autophagosome formation. The RFC4-STK38 interaction facilitates BECN1 recruitment, thereby activating autophagy. Phosphorylation of STK38 at T444 stabilizes this complex, whereas a phospho-deficient mutant impairs autophagy. In vivo, RFC4 overexpression confers TMZ resistance, reversible by autophagy inhibition. Thus, our findings identify the RFC4-STK38-BECN1 axis as a mechanism underlying TMZ resistance and a potential target for precision therapy in GBM.

PMID:41872171 | DOI:10.1038/s41467-026-70798-1

Received — 5 March 2026 ⏭

Weight Space Representation Learning via Neural Field Adaptation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhuoqian Yang, Mathieu Salzmann, Sabine S\"usstrunk
5 March 2026 at 13:00
arXiv:2512.01759v2 Announce Type: replace-cross Abstract: In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.
Received — 17 February 2026 ⏭

pFedNavi: Structure-Aware Personalized Federated Vision-Language Navigation for Embodied AI

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qingqian Yang · Hao Wang · Sai Qian Zhang · Jian Li · Yang Hua · Miao Pan · Tao Song · Zhengwei Qi · Haibing Guan
17 February 2026 at 13:00
arXiv:2602.14401v1 Announce Type: cross Abstract: Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns. Federated Learning FL mitigates this by keeping data on-device, but vanilla FL struggles under VLNs' extreme cross-client heterogeneity in environments and instruction styles, making a single global model suboptimal. This paper proposes pFedNavi, a structure-aware and dynamically adaptive personalized federated learning framework tailored for VLN. Our key idea is to personalize where it matters: pFedNavi adaptively identifies client-specific layers via layer-wise mixing coefficients, and performs fine-grained parameter fusion on the selected components (e.g., the encoder-decoder projection and environment-sensitive decoder layers) to balance global knowledge sharing with local specialization. We evaluate pFedNavi on two standard VLN benchmarks, R2R and RxR, using both ResNet and CLIP visual representations. Across all metrics, pFedNavi consistently outperforms the FedAvg-based VLN baseline, achieving up to 7.5% improvement in navigation success rate and up to 7.8% gain in trajectory fidelity, while converging 1.38x faster under non-IID conditions.
There are no more articles
❌