Tag
# Paper page - Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs Source: [https://huggingface.co/papers/2605.07447](https://huggingface.co/papers/2605.07447) ## Abstract SAEgis detects adversarial attacks on vision\-language models using sparse autoencoders trained for reconstruction, achieving strong performance across domains without additional training\. [Vision\-language models](https://huggingface.co/papers?q=Vision-language%20models)\(VLMs\) have advan
# Paper page - MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning Source: [https://huggingface.co/papers/2605.07850](https://huggingface.co/papers/2605.07850) We propose**MatryoshkaLoRA**, a general, Matryoshka\-inspired training framework for LoRA that learns accurate hierarchical low\-rank representations by inserting a fixed, carefully crafted diagonal matrix**P**between the existing LoRA adapters to scale their sub\-ranks accordingly\. By introducing
# Paper page - Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning Source: [https://huggingface.co/papers/2605.06734](https://huggingface.co/papers/2605.06734) Authors: , , , , , , , , , , , , , , , , , ## Abstract Quantum\-inspired fast\-weight programming framework using single\-qubit circuits achieves superior forecasting performance with reduced parameters compared to classical recurrent models while maintaining NISQ device compatibility\. [Fast Weight Programmers](https://huggingfac
# Paper page - MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation Source: [https://huggingface.co/papers/2512.18181](https://huggingface.co/papers/2512.18181) ## Abstract MACE\-Dance is a music\-driven dance video generation framework that combines cascaded Mixture\-of\-Experts with diffusion models and specialized training strategies to achieve high\-quality visual appearance and realistic human motion\. With the rise of online dance\-video platforms and rapi
# Paper page - Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Source: [https://huggingface.co/papers/2605.06169](https://huggingface.co/papers/2605.06169) **Mean Mode Screaming \(MMS\)**— the abrupt entry event into a silent, mean\-dominated collapse state in ultra\-deep Diffusion Transformers\. Optimization can remain stable for thousands of steps and then diverge within a few updates, with the loss returning to near its initialization level\. We trace
# Paper page - PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors Source: [https://huggingface.co/papers/2605.06455](https://huggingface.co/papers/2605.06455) ## Abstract PrefixGuard enables effective online monitoring of LLM agents through trace analysis and prefix\-based risk scoring, demonstrating strong performance across multiple benchmark tasks while providing diagnostic insights for alert reliability\. Large language model \(LLM\) agents now execute long, tool\-using ta
# Paper page - R^3-SQL: Ranking Reward and Resampling for Text-to-SQL Source: [https://huggingface.co/papers/2604.25325](https://huggingface.co/papers/2604.25325) ## Abstract R$^3$\-SQL addresses inconsistencies in scoring functionally equivalent SQL queries and improves candidate recall through unified reward ranking and agentic resampling techniques\. Modern[Text\-to\-SQL](https://huggingface.co/papers?q=Text-to-SQL)systems generate multiple candidate[SQL queries](https://huggingface.co/papers