跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1020新增论文
+819其中 AI 相关
+116已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 14:52各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 16:47 — 2026-11-20 16:47(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 14:52库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,429 已收录论文23,606 AI 相关8,718 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2611.20625

ASCG: Adaptive Spatial Classifier Guidance for Surgical Concept Suppression in Diffusion Models

Younghwan Kil, Joonhyeong Park, Giung Nam, Juho Lee

原文摘要

While text-to-image (T2I) diffusion models achieve remarkable quality, they risk producing harmful content. Existing safety mechanisms often rely on indiscriminate, global interventions that induce unintended semantic drift and degrade image quality. To address this, we propose Adaptive Spatial Classifier Guidance (ASCG), a necessity-driven framework that employs probabilistic monitoring to activate guidance selectively upon harm detection. By leveraging Grad-CAM for localized suppression, ASCG effectively removes harmful concepts while preserving superior semantic fidelity compared to conventional methods. Furthermore, we overcome the limitations of traditional metrics like NudeNet---which fails to assess semantic integrity---by introducing a VLM-based evaluation framework to provide a fine-grained, robust analysis of both safety and context preservation. Our results demonstrate that ASCG not only balances safety and fidelity but also exhibits remarkable plug-and-play synergy with existing frameworks to establish state-of-the-art performance.

cs.CV

新论文 · v1arXiv:2611.20623

Example-Based Spatial Guidance for Training-Free Concept Erasure in Diffusion Models

Younghwan Kil, Giung Nam, Joonhyeong Park, Jinwoo Shin, Juho Lee

原文摘要

Text-to-image (T2I) diffusion models often synthesize policy-violating content, necessitating robust safeguards and rigorous evaluation frameworks. However, current approaches remain largely monolithic in both execution and evaluation, limited to coarse-grained categorization within broad unsafe concepts. Such approaches fail to account for the specific constituent factors of a violation, resulting in weak learning signals and allowing model collapse to bypass safety checks. To overcome these limitations, we propose Example-Based Spatial Guidance (EBSG), a training-free method that utilizes user-editable exemplar packs to provide granular spatial guidance for precise concept steering. Unlike existing methods that coarsely steer the entire image away from a broad concept, EBSG decomposes these categories into specific sub-concepts via exemplar text-image pairs, providing explicit, localized steering signals for more robust safety control. Furthermore, we introduce a vision language model (VLM)-based evaluation protocol that provides a fine-grained assessment, avoiding the pitfall of conventional binary evaluators that permit model collapse to bypass safety checks. Empirically, EBSG achieves state-of-the-art erasure performance across diverse safety datasets and concept categories, spanning four nudity benchmarks, seven I2P harmful-concept slices, and four MJA metaphor categories, while supporting multi-concept removal and transferring to a modern backbone, SD3.

cs.CV

新论文 · v1arXiv:2611.07558

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking

Moonseok Choi, Jongwon Jeong, Minki Kang, Giung Nam, Juho Lee

原文摘要

Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time. Whereas existing compression methods target unconstrained generation, we first identify a fundamental mismatch: under structured generation, grammar constraints reduce the model's output distribution to valid tokens, and the logits matter most at the small set of positions that decide the agent's action. Motivated by this finding, we propose SKIM (Selective Knowledge-Informed Masking), the first pruning and distillation framework for LLM agents under structured generation, with both stages guided by token role. SKIM partitions token positions into context, decision, and format categories, and this partition drives two complementary axes: (1) category-aware pruning saliency scores that preserve parameters most relevant for decision positions; and (2) an on-policy distillation objective that aligns student and teacher on valid tokens, paired with category-aware feature matching. We evaluate SKIM on tool-calling benchmarks and within multi-step agent loops, across multiple model scales and sparsity levels. SKIM consistently improves accuracy over baselines, with its superiority becoming most striking in high-sparsity regimes where conventional methods struggle, demonstrating the potential of category-aware compression for deployment-time grammar-constrained agents.

cs.CL · cs.AI