January 2026

arXiv:2601.03431v1 Announce Type: new Abstract: We present WeedRepFormer, a lightweight multi-task Vision Transformer designed for simultaneous waterhemp segmentation and gender classification. Existing agricultural models often struggle to balance the fine-grained feature extraction required for biological attribute classification with the efficiency needed for real-time deployment. To address this, WeedRepFormer systematically integrates structural reparameterization across the entire architecture – comprising a Vision Transformer backbone, a Lite R-ASPP decoder, and a novel reparameterizable classification head – to decouple training-time capacity from […]

Ver mais

arXiv:2601.03430v1 Announce Type: new Abstract: Open Source Software for Social Good (OSS4SG) projects aim to address critical societal challenges, such as healthcare access and community safety. Understanding the community dynamics and contributor patterns in these projects is essential for ensuring their sustainability and long-term impact. However, while extensive research has focused on conventional Open Source Software (OSS), little is known about how the mission-driven nature of OSS4SG influences its development practices. To address this gap, we conduct a […]

Ver mais

arXiv:2601.03429v1 Announce Type: new Abstract: Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between interpretability and privacy. Although prior work has shown that explanation methods can leak membership information, practitioners still lack systematic guidance on selecting or deploying explanation techniques that balance transparency with privacy. We present DeepLeak, a system to audit and mitigate privacy risks in […]

Ver mais

arXiv:2601.03425v1 Announce Type: new Abstract: Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a post hoc framework that analyzes routing behavior at the level of expert groups rather than individual experts. Across three representative models and the MMLU benchmark, we uncover a domain-invariant Standing Committee. This is a compact coalition of routed experts that consistently captures the majority of routing mass across […]

Ver mais

arXiv:2601.03424v1 Announce Type: new Abstract: Behavioral benchmarks tell us textit{what} a model does, but not textit{how}. We introduce a training-free mechanistic probe using attention-graph spectra. Treating each layer as a token graph, we compute algebraic connectivity ($lambda_2$), smoothness, and spectral entropy. Across 12 models and 10 languages, these measures yield stable “spectral fingerprints” that expose discontinuities missed by standard evaluation. We report four results. (1) Models undergoing specific curriculum transitions (e.g., code-to-chat) show an English-only, syntax-triggered connectivity failure […]

Ver mais

arXiv:2601.03423v1 Announce Type: new Abstract: Adapting language models to the clinical domain through continued pretraining and fine-tuning requires costly retraining for each new model generation. We propose Cross-Architecture Proxy Tuning (CAPT), a model-ensembling approach that enables training-free adaptation of state-of-the-art general-domain models using existing clinical models. CAPT supports models with disjoint vocabularies, leveraging contrastive decoding to selectively inject clinically relevant signals while preserving the general-domain model’s reasoning and fluency. On six clinical classification and text-generation tasks, CAPT with […]

Ver mais

arXiv:2601.03420v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial jailbreaks is essential. However, current safety evaluations often overestimate robustness because existing automated attacks are limited by restrictive assumptions. They typically rely on handcrafted priors or require white-box access for gradient propagation. We challenge these constraints by demonstrating that token-level iterative optimization can succeed without gradients or priors. We introduce RAILS (RAndom Iterative Local Search), a […]

Ver mais

arXiv:2601.03418v1 Announce Type: new Abstract: Verifying system-generated summaries remains challenging, as effective verification requires precise attribution to the source context, which is especially crucial in high-stakes medical domains. To address this challenge, we introduce PCoA, an expert-annotated benchmark for medical aspect-based summarization with phrase-level context attribution. PCoA aligns each aspect-based summary with its supporting contextual sentences and contributory phrases within them. We further propose a fine-grained, decoupled evaluation framework that independently assesses the quality of generated summaries, citations, […]

Ver mais

arXiv:2601.03417v1 Announce Type: new Abstract: Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit structured memories offer interpretability but often become brittle under long-context overload, while latent memory mechanisms are efficient and stable yet difficult to inspect. We propose LatentGraphMem, a memory framework that combines implicit graph memory with explicit subgraph retrieval. LatentGraphMem stores a graph-structured memory […]

Ver mais

arXiv:2601.03416v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous work has shown that increasing inference steps can disrupt safety mechanisms and lead MLLMs to generate attacker-desired harmful content. However, most existing attacks focus on increasing the complexity of the modified visual task itself and do not explicitly leverage the model’s own reasoning incentives. This leads to them underperforming on reasoning models (Models with […]

Ver mais