Concept Acupuncturist (ConceptACP) is a machine‑unlearning framework that removes targeted concepts from diffusion models efficiently and precisely. It identifies the most relevant cross‑attention block in the U‑Net denoiser, fine‑tunes only that block, and uses Sparse Autoencoders to generate semantically meaningful correction signals for concept erasure. Applied to SDXL‑Turbo, ConceptACP boosts forgetting success by over 36 percentage points while maintaining image quality and prompt fidelity, and works across other Stable Diffusion backbones.
By Yiran Xiahou, Siliang Qin, Kai Chen, Shengzhi Zhang, Renyang Liu
arXiv:2610.32075v1 Announce Type: new
Abstract: Feed-forward neural renderers synthesize global illumination across novel 3D scenes without per-scene optimization or runtime ray tracing. Existing tra...
By Sarah Zhang, Zhiyang Dou, Minghao Guo, Benjamin Tod Jones, Wojciech Matusik
arXiv:2610.32182v1 Announce Type: cross
Abstract: Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorly understood. We present a li...
By Muhammad Zeeshan Karamat, Syed Talal Hassan, Christiana Chamon Garcia
arXiv:2610.32708v1 Announce Type: new
Abstract: Continual learning (CL) aims to learn from sequential tasks while mitigating catastrophic forgetting when historical data are no longer accessible. We...
By Jingyi Guo, Runze Li, Lingzhou Xue
arXiv:2601.16200v4 Announce Type: replace-cross
Abstract: Modern deep learning models exhibit strong capabilities across diverse applications, yet remain vulnerable to malicious inputs that induce er...
By Song Xia, Meiwen Ding, Chenqi Kong, Wenhan Yang, Xudong Jiang
arXiv:2602.08934v3 Announce Type: replace-cross
Abstract: AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unc...
By Suraj Ranganath, Atharv Ramesh
arXiv:2601.13707v3 Announce Type: replace-cross
Abstract: Hallucinations in large vision--language models (LVLMs) often arise when language priors dominate over visual evidence, leading to object mis...
By Yujin Jo, Sangyoon Bae, Taesup Kim
arXiv:2412.01090v3 Announce Type: replace
Abstract: Video depth estimation is essential for applications such as autonomous driving, AR/VR, and robotics. Recent transformer-based single-image monocul...
By Sunghun Yang, Minhyeok Lee, Suhwan Cho, Jungho Lee, Sangyoun Lee
Language models now answer questions alongside other claims: a note in the system prompt, a message from another agent, their own earlier answer. We ask what it takes to talk a model out of an answer...
This paper introduces Scope-Gap Injection (SGI), an indirect prompt injection method for multi-stage LLM-agent safety pipelines. In the IJCAI 2026 OpenClaw Agent Security Attack Competition, each atta...
Text injection trains speech recognition models on unpaired text alongside paired audio. We feed the speech encoder synthetic input derived from text so the whole model learns from it. Previously, we...
Decentralized multi-agent systems (MAS) enable large language model agents to interact without centralized control. Agents need to adapt to other agents at test time and reuse accumulated experience t...
Generative machine learning provides an end-to-end framework for aerodynamic design optimization by generating diverse aerodynamic configurations conditioned on target performance. However, the genera...
Time Series Foundation Models have demonstrated that pretraining on diverse datasets enables effective transfer to new forecasting tasks. Classical methods like ARIMA, however, remain configured and t...
The article provides a practical guide on implementing guardrails for a local large language model (LLM) agent. It focuses on using Gemma 4, Ollama, and the OpenAI Agents SDK to set up these safety measures. The post is published on Towards Data Science.
By Shuai Guo
Graph Neural Networks are widely used to learn structural representations of relational data. Hierarchical graph pooling learns multi-level representations by progressively coarsening graphs; however,...
OpenAI details the measures taken to enhance containment in its frontier model training environment. The company highlights the use of offline environments and high‑compute red‑teaming to strengthen security during training and evaluation. These steps aim to protect the integrity of the model development process.
AgentDreamer is an agent-guided optimization framework that aligns text instructions with simulated 3D motion by using an off-the-shelf agent to generate a structured semantic motion prior. The prior specifies what should move, in which direction, and in what temporal order, and is represented as parametric functions over temporal chunks to produce dense 3D trajectories. These trajectories are then used to optimize a differentiable MPM simulator so that its rollout matches the prior while respecting scene dynamics, and the framework introduces Motion-IG, an information‑theoretic metric for measuring text‑motion alignment.
By Mijeong Kim, Suho Park, Junha Park, Bohyung Han
The paper introduces DynaCertBench, a benchmark of 105 diverse systems for certifying stability, safety, and related properties, and presents LLM2Cert, a framework that uses large language models to generate and verify candidate certificates via SMT solvers or Lean. LLM2Cert achieves a 77.1% verification rate on the benchmark, improving by 17.1 percentage points over a single-shot approach, and successfully verifies 22 certificates that All-SMT could not resolve. The authors provide code and data on GitHub for reproducibility.
By Zhipeng Cao, Peiyang Song, Nikolaus Vertovec, Weiru Cui, Zhihao Yang, Mingkang Liu, Luxia Lin, Bai Xue, Alessandro Abate
DeepLook is a training‑free decoding framework that uses segment‑level confidence to guide branching during inference. It only expands the search tree at points of high uncertainty and ranks candidate continuations by Average Lookahead Confidence (ALC), a mean confidence over fixed‑horizon rollouts, before finalizing and voting on a pruned subset. Experiments on four mathematics benchmarks show that DeepLook matches or surpasses DeepConf‑low in 12 of 16 settings while reducing token usage by 87.3%, though its advantage disappears on the knowledge‑intensive GPQA‑Diamond task due to hallucinations receiving high ALC.
By Tingxin Yang, Zefeng Wang, Mengyue Wang, Jinhe Bi, Xingcheng Zhou, Volker Tresp, Yunpu Ma