❌

Normal view

Received — 15 September 2026 ⏭

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Danning Zhang · Yijing Lin · Shuhan Zhuang · Mengqi Huang · Shaojin Wu · Shancheng Fang · Zhendong Mao
14 September 2026 at 12:00
arXiv:2609.12397v1 Announce Type: cross Abstract: Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement of generative models, their evaluation remains largely lagging. Existing methods, whether embedding-based or Multi-modal Large Language Model (MLLM)-based, evaluate alignment with each modal condition in isolation, which contradicts the simultaneous condition alignment objective of multi-modal image generation, leading to poor consistency with human judgments. To address this challenge, we propose UFO, the first unified framework for omni-condition alignment simultaneous evaluation. Specifically, UFO introduces a novel Atomized Chain-of-Evaluation paradigm, \emph{i.e.}, it first decomposes omni-condition alignment into a sequential chain of fine-grained, disentangled Atomic Evaluation Units (AEUs), categorizes them into distinct modality-relevance classes, and then employs general or dedicated functional calls for accurate verification of different AEU types. Experimental results demonstrate that UFO achieves the highest correlation with human evaluation preferences, delivering an average improvement of 15.25\%. Furthermore, we present UFO-Bench, a dedicated benchmark designed to holistically evaluate the performance of existing customization models under the diverse mutual interactions of textual and visual conditions.
Received — 2 April 2026 ⏭

AI-guided multi-omics analysis identifies NPC1-modulated susceptibility to SARS-CoV-2 infection under PM(2.5) exposure

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Guoqing Feng · Zheng Dong · Limei Ke · Weilai Zhou · Yu Tian · Xingtian Li · Wenxin Xiang · Yanjun Li · Qi Huang · Linfeng Liu · Bo Yin · Shouyi Yan · Jianxiu Liu · Xindong Ma · Huaiyong Chen · Miao He · Ke Hao · Sijin Liu · Qian Di
30 March 2026 at 18:00

Nat Commun. 2026 Mar 30. doi: 10.1038/s41467-026-71196-3. Online ahead of print.

ABSTRACT

Exposure to airborne fine particulate matter (PM2.5) has been linked to increased risk of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, yet the underlying mechanisms remain unclear. Here, by leveraging a fine-tuned foundation model of single-cell transcriptomics, we uncover shared transcriptional signatures between PM2.5 exposure and SARS-CoV-2 infection. We further validate this association using population-level epidemiological analyses and perform genome-wide association studies (GWAS) to identify genetic variants that modulate infection risk under PM2.5 exposure. In addition, we identify NPC1 as a key modulator involved in SARS-CoV-2 infection efficiency under virus-laden PM2.5 exposure through integrative functional genomic analyses and in vitro experiments. Our findings suggest that PM2.5 facilitates viral entry through an NPC1-modulated endo-lysosomal pathway, providing a mechanistic explanation for observed pollution-related susceptibility. By integrating artificial intelligence (AI)-guided transcriptomics, epidemiology, GWAS, functional genomics, and in vitro verification, our study elucidates how environmental and genetic factors jointly influence SARS-CoV-2 susceptibility. This work highlights how AI-assisted multi-omics integration systematically decodes the health impacts of environmental exposures from molecular to population levels and informs air quality policy and infectious disease preparedness.

PMID:41912520 | DOI:10.1038/s41467-026-71196-3

Received — 14 March 2026 ⏭

CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dengcan Liu · Fengkai Yang · Xiaohan Wang · Shurui Yan · Jiajun Chai · Jiahao Li · Yikun Ban · Zhendong Mao · Wei Lin · Guojun Yin
10 March 2026 at 12:00
arXiv:2603.08035v1 Announce Type: new Abstract: Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based approaches enhance evaluation transparency, they lack systematic quality control, yielding noisy and redundant criteria, failing to mitigate persistent biases (e.g., verbosity, position) in LLM evaluators, and creating a scalability-reliability trade-off. To address these limitations, we propose CDRRM (Contrast-Driven Rubric Reward Model), a framework built on a novel Contrast-then-Synthesis paradigm for high-quality rubric generation and guided preference judgment. CDRRM first conducts multi-dimensional contrastive profiling on preference pairs to identify causal discriminative factors, then synthesizes these insights into compact, context-aware rubrics to guide preference judg- ments. Extensive experiments on three authoritative benchmarks (RewardBench, RMBench, RMB) demonstrate that CDRRM achieves state-of-the-art performance across diverse domains and effectively mitigates aforementioned evaluation biases. Notably, our approach delivers exceptional data efficiency: training the rubric generator on only 3k high-quality samples empowers a frozen pre-trained judge model to outperform fully fine-tuned baselines. This work offers a scalable, interpretable, and data-efficient path for reward modeling.
Received — 11 March 2026 ⏭

Accelerating Robotic Reinforcement Learning with Agent Guidance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haojun Chen · Zili Zou · Chengdong Ma · Yaoxiang Pu · Haotong Zhang · Yuanpei Chen · Yaodong Yang
10 March 2026 at 12:00
arXiv:2602.11978v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application is stifled by low sample efficiency. Recent Human-in-the-Loop (HIL) methods accelerate training by using human corrections, yet this approach faces a scalability barrier. Reliance on human supervisors imposes a 1:1 supervision ratio that limits scalability, suffers from operator fatigue over extended sessions, and introduces high variance due to inconsistent human proficiency. We present Agent-guided Policy Search (AGPS), a framework that automates the training pipeline by replacing human supervisors with a multimodal agent. Our key insight is that the agent can be viewed as a semantic world model, injecting intrinsic value priors to structure physical exploration. By using tools, the agent provides precise guidance via corrective waypoints and spatial constraints for exploration pruning. We validate our approach on three tasks, ranging from precision insertion to deformable object manipulation. Results demonstrate that AGPS outperforms HIL methods in sample efficiency. This automates the supervision pipeline, unlocking the path to labor-free and scalable robot learning. Project website: https://agps-rl.github.io/agps/.
Received — 5 March 2026 ⏭

PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hung Manh Pham · Jinyang Wu · Xiao Ma · Yiming Zhang · Yixin Xu · Aaqib Saeed · Bin Zhu · Zhou Pan · Dong Ma
5 March 2026 at 13:00
arXiv:2603.03331v1 Announce Type: cross Abstract: Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide supervision in the form of numerical measurements or task-specific labels, limiting their suitability for language-based physiological reasoning and multimodal foundation models. In this work, we introduce PulseLM, a large-scale PPG-text dataset designed to bridge raw PPG waveforms and natural language through a unified, closed-ended question answering (QA) formulation. PulseLM aggregates PPG recordings from fifteen publicly available sources and harmonizes heterogeneous annotations into twelve common physiologically QA tasks. The dataset comprises 1.31 million standardized 10-second PPG segments, associated with 3.15 million question-answer pairs. We further define reproducible preprocessing, supervision, and evaluation protocols and establish baseline benchmarks using multimodal PPG-aware large language models. PulseLM provides a standardized foundation for studying multimodal physiological reasoning, cross-dataset generalization, and scalable benchmarking of PPG-based language models. The data and code can be found publicly available at: https://github.com/manhph2211/PulseLM.
There are no more articles
❌