arXiv:2507.05660v2 Announce Type: replace-cross
Abstract: Customizing Large Language Models (LLMs) on untrusted datasets poses severe risks of injecting toxic behaviors. In this work, we introduce Optimus, a novel defense framework designed to mitigat…
When Daniel Rhyne pleaded guilty on April 1 to having launched an insider extortion attack against his then-employer, authorities enumerated the techniques he used, including unauthorized remote desktop sessions, deletion of netw…
arXiv:2604.01501v1 Announce Type: cross
Abstract: Causal mediation analysis provides techniques for defining and estimating effects that may be endowed with mechanistic interpretations. With many scientific investigations seeking to address mechanisti…
arXiv:2604.00931v2 Announce Type: new
Abstract: Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their pro…
arXiv:2604.01007v2 Announce Type: new
Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requ…
arXiv:2604.00590v2 Announce Type: cross
Abstract: In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there …
arXiv:2604.02048v1 Announce Type: new
Abstract: Developing vision-language models (VLMs) that generalize across diverse tasks requires large-scale training datasets with diverse content. In English, such datasets are typically constructed by aggregati…
arXiv:2604.02055v1 Announce Type: new
Abstract: Accurate reproduction of facial skin tone is essential for realism, identity preservation, and fairness in Virtual Human (VH) rendering. However, most accessible avatar creation pipelines rely on photogr…
arXiv:2603.29966v2 Announce Type: replace
Abstract: Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent…
arXiv:2604.02073v1 Announce Type: new
Abstract: Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thought (CoT) rationales be…