❌

Normal view

Received — 10 September 2026 ⏭

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qisong He · Jinwei Hu · Xinmiao Huang · Changshun Wu · Yi Dong · Xiaowei Huang
10 September 2026 at 12:00
arXiv:2605.14175v2 Announce Type: replace Abstract: In a long conversation, an LLM can produce a plausible continuation that rests on premises the conversation has already abandoned. No runtime check ties its output to what the conversation has established, a gap that context-manipulation attacks on deployed agents exploit. We close this gap with a runtime verifier: an LLM Interpreter classifies each utterance into one of eight epistemic operations, and a symbolic engine applies them to a dependency map that records what every claim rests on and whether it still stands. Whether a continuation is grounded reduces to a walk over the map, linear in its size, with no LLM call. Retraction propagates through the same map with a conflict-free guarantee, flagging exactly the conclusions that lose support. On ReviseQA for belief revision and MemoryAgentBench's fact-consolidation split, two third-party benchmarks where earlier premises are superseded, the verifier leads a budget-matched retrieval baseline across five QA models and lifts MemoryAgentBench single-hop accuracy from 0.46--0.95 to 0.93--0.98. With the verifier, even the 7B model overtakes unaided GPT-4o. These runs feed the engine the benchmarks' own structured updates. When a GPT-4o Interpreter extracts every update from raw text instead, accuracy is statistically unchanged. Per-query cost is flat in conversation length, prompts staying near 0.8k tokens where full context reaches 114k and retraction queries under a microsecond at 2000 turns.
Received — 6 April 2026 ⏭

Multi-ancestry transcriptome prediction with functionally informed variants in TOPMed MESA improves performance of transcriptome-wide association studies

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Xiaowei Hu · Daniel S Araujo · Chachrit Khunsriraksakul · Lida Wang · Quan Sun · Jia Wen · Lingbo Zhou · Lynette Ekunwe · Leslie A Lange · Ethan M Lange · Stephen B Montgomery · Alexander P Reiner · Francois Aguet · Kristin G Ardlie · Tuuli Lappalainen · Christopher R Gignoux · Esteban G Burchard · Kent D Taylor · Xiuqing Guo · Jerome I Rotter · Stephen S Rich · Elaine Cornell · Peter Durda · Russell P Tracy · Yongmei Liu · W Craig Johnson · George P Papanicolaou · Minoli A Perera · Michael H Cho · Dajiang J Liu · Laura M Raffield · Yun Li · TOPMed Multi-Omics Working Group · Heather E Wheeler · Hae Kyung Im · Ani Manichaikul
3 April 2026 at 18:00

Am J Hum Genet. 2026 Apr 2;113(4):828-841. doi: 10.1016/j.ajhg.2026.03.008.

ABSTRACT

Reliable reference transcriptome prediction models are key to accurate multi-ancestry transcriptome-wide association studies (TWASs). We propose three methods leveraging functionally informed variants (FIVs) for transcriptome prediction models to improve multi-ancestry TWASs. We trained models on 1,287 multi-ancestry participants from the Trans-Omics for Precision Medicine (TOPMed) program Multi-Ethnic Study of Atherosclerosis (MESA) with RNA sequencing (RNA-seq) data from peripheral blood mononuclear cells (PBMCs). We validated models' prediction accuracy on two external independent datasets, Geuvadis and Jackson Heart Study. To test robustness of our methods for TWASs, we integrated models with three multi-ancestry GWASs from blood cell, lipid, and pulmonary function traits, respectively. Our methods presented similar prediction accuracy while using a smaller and functionally informed set of variants compared to the benchmark method, elastic net (EN). Overall, our methods achieved higher power and accuracy (with average improved accuracy of 24% over EN) for TWASs. However, no single proposed method outperformed all GWAS traits. To further improve TWAS performance, we propose an omnibus approach that aggregates TWAS summary statistics from our methods. The omnibus approach yielded the highest number of Bonferroni-significant TWAS genes for all GWAS traits, and it further improved TWAS power and accuracy for blood cell traits. Additionally, the omnibus approach detected some trait-relevant important genes that the EN missed. Our study demonstrates the value of including FIVs in multi-ancestry transcriptome prediction models for improving TWAS performance. Further, the observed TWAS improvement depends on the GWAS trait's relevance to the PBMCs used to build our transcriptome prediction models.

PMID:41932314 | DOI:10.1016/j.ajhg.2026.03.008

Received — 26 March 2026 ⏭

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zining Fang · Chunhui Liu · Bin Xu · Ming Chen · Xiaowei Hu · Cheng Xue
25 March 2026 at 12:00
arXiv:2603.22844v2 Announce Type: new Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.
There are no more articles
❌