❌

Normal view

Received — 10 September 2026 ⏭

Distilling Image Prototypes for Guided Test-Time Adaptation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Liwen Wang · Xingbo Dong · Iman Yi Liao · Deyin Liu · Massimo Tistarelli · Lin Yuanbo Wu · Zhe Jin
10 September 2026 at 12:00
arXiv:2609.09737v1 Announce Type: cross Abstract: Test-Time Adaptation (TTA) enhances the robustness of models against distribution shifts but faces two critical challenges: error accumulation from noisy pseudo-labels and catastrophic forgetting of source knowledge. Uncertainty-based approaches designed to mitigate error accumulation often yield overconfident or computationally expensive estimates, while strategies intended to prevent forgetting via prototype replay rely on static representations that easily become misaligned as the model adapts. To address these issues, this paper proposes a novel framework, Distilling Image Prototype for Guided Test-Time Adaptation (DIPTTA). The core of the proposed approach is the introduction of a Distill Image Prototype (DIP), a compact set of synthetic images that serves as a dynamic and regenerative anchor of source knowledge. This prototype enables a dynamic feature replay mechanism that continuously generates feature prototypes aligned with the current state of the model, thus effectively preventing catastrophic forgetting. Furthermore, the DIP anchors a source-calibrated uncertainty estimation method, which provides a less biased measure of sample reliability by leveraging stable source knowledge, thereby robustly suppressing error accumulation. Extensive experiments on multiple benchmarks demonstrate that DIPTTA significantly outperforms state-of-the-art methods, particularly under severe domain shifts. The source code is available at https://github.com/LiwenWang919/DIPTTA.
Received — 27 May 2026 ⏭

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xu Yao · Siyuan Zhou · Zhenbo Wu · Chaochuan Hou · Shuang Liang · Shiping Wang · Hailiang Huang · Songqiao Han · Minqi Jiang
26 May 2026 at 12:00
arXiv:2605.26068v2 Announce Type: cross Abstract: Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address unique challenges or share fundamental mechanics. This paper introduces WSADBench, the first benchmark that unifies evaluation across distinct weakly supervised scenarios, benchmarking diverse approaches from specialized WSAD methods to advanced tabular foundation models. WSADBench establishes standardized protocols to evaluate 36 algorithms across 4 modalities by systematically varying label quantity, granularity, and quality, revealing the performance boundaries of various methods. Based on over 700K experiments, WSADBench reveals four critical insights: (i) Strong intrinsic correlations exist between these weak supervision scenarios, challenging the isolation of current research directions. (ii) Specialized WSAD algorithms excel only in extreme label-scarcity regimes but are quickly dominated by tabular foundation models and general classification methods as supervision increases or in OOD scenarios. (iii) Unlabeled data shows inconsistent utility across settings, with marginal gains compared to label refinement. (iv) Models exhibit asymmetric sensitivity to different types of label noise. We release WSADBench as an open-source benchmark with code and datasets to facilitate future WSAD research: https://github.com/SUFE-AILAB/WSADBench.
Received — 4 April 2026 ⏭

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
3 April 2026 at 18:00

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
3 April 2026 at 18:00

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

Received — 2 April 2026 ⏭

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

✇cs.AI, q-bio.NC updates on arXiv.org
By: Michael Hind · Basel Shbita · Bo Wu · Farhan Ahmed · Chad DeLuca · Nathan Fulton · David Cox · Dan Gutfreund
1 April 2026 at 12:00
arXiv:2603.22519v2 Announce Type: replace-cross Abstract: Textual Large Language Models (LLMs) provide a simple and familiar interface: a string of text is used for both input and output. However, the information conveyed to an LLM often has a richer structure and semantics, which is not conveyed in a string. For example, most prompts contain both instructions ("Summarize this paper into a paragraph") and data (the paper to summarize), but these are usually not distinguished when passed to the model. This can lead to model confusion and security risks, such as prompt injection attacks. This work addresses this shortcoming by introducing an LLM-native mark-up language, LLMON (LLM Object Notation, pronounced "Lemon"), that enables the structure and semantic metadata of the text to be communicated in a natural way to an LLM. This information can then be used during model training, model prompting, and inference implementation, leading to improvements in model accuracy, safety, and security. This is analogous to how programming language types can be used for many purposes, such as static checking, code generation, dynamic checking, and IDE highlighting. We discuss the general design requirements of an LLM-native markup language, introduce the LLMON markup language and show how it meets these design requirements, describe how the information contained in a LLMON artifact can benefit model training and inference implementation, and provide some preliminary empirical evidence of its value for both of these use cases. We also discuss broader issues and research opportunities that are enabled with an LLM-native approach.
Received — 26 March 2026 ⏭

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

✇cs.AI, q-bio.NC updates on arXiv.org
By: Michael Hind · Basel Shbita · Bo Wu · Farhan Ahmed · Chad DeLuca · Nathan Fulton · David Cox · Dan Gutfreund
25 March 2026 at 12:00
arXiv:2603.22519v1 Announce Type: cross Abstract: Textual Large Language Models (LLMs) provide a simple and familiar interface: a string of text is used for both input and output. However, the information conveyed to an LLM often has a richer structure and semantics, which is not conveyed in a string. For example, most prompts contain both instructions ("Summarize this paper into a paragraph") and data (the paper to summarize), but these are usually not distinguished when passed to the model. This can lead to model confusion and security risks, such as prompt injection attacks. This work addresses this shortcoming by introducing an LLM-native mark-up language, LLMON (LLM Object Notation, pronounced "Lemon"), that enables the structure and semantic metadata of the text to be communicated in a natural way to an LLM. This information can then be used during model training, model prompting, and inference implementation, leading to improvements in model accuracy, safety, and security. This is analogous to how programming language types can be used for many purposes, such as static checking, code generation, dynamic checking, and IDE highlighting. We discuss the general design requirements of an LLM-native markup language, introduce the LLMON markup language and show how it meets these design requirements, describe how the information contained in a LLMON artifact can benefit model training and inference implementation, and provide some preliminary empirical evidence of its value for both of these use cases. We also discuss broader issues and research opportunities that are enabled with an LLM-native approach.
There are no more articles
❌