cập nhật 8 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5388, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

24
Can you make models believe false facts in the prompt?
📄 Paper arXiv cs.AI 15 giờ trước

arXiv:2611.23938v1 Announce Type: new Abstract: Making LLMs believe false facts is useful for alignment evaluations and for building model organisms. Previous work explored doing so with Synthetic Document Finetuning (SDF). But SDF requires fine-tuning one new model for each set…

🅲 hạng C
24
Erased but Recoverable: On the Fragility of Concept Erasure Under Fine-Tuning
📄 Paper arXiv cs.CR 15 giờ trước

arXiv:2611.24220v1 Announce Type: new Abstract: Existing concept erasure methods for text-to-image diffusion models primarily focus on suppressing target concepts while preserving non-target generation quality. However, in practical applications, open-source diffusion models are…

🅲 hạng C
23
HINT-WAM: Hindsight-Informed Training for World Action Models
📄 Paper HF Daily Papers 2 ngày trước

World action models (WAMs) have shown promising generalization and data efficiency in robot manipulation by coupling action generation with predictions of future visual dynamics. Translating these capabilities into reliable task execution, however, remains a challenge for existin…

🅲 hạng C
22
Late Entry in Looped Language Models
📄 Paper HF Daily Papers 2 ngày trước

Looped language models deepen reasoning at a compact parameter count by iterating a shared layer stack T times per token, turning recurrence depth directly into sequential decoding latency. Conventional early-exit decoding halts after initial passes without cache completion, trun…

🅲 hạng C
22
Chain-of-Thought Controllability Can Reduce Chain-of-Thought Monitorability
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.21799v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting hidden goals, off-task behavior, and other failures in AI agents. One risk is that models could deliberately shape their reasoning to make it opaque to monitors. W…

🅲 hạng C
22
Fine-Grained Japanese Clinical Named Entity Recognition: A Controlled Comparison of BERT and Open-Weight Large Language Models
📄 Paper arXiv cs.AI 1 ngày trước

arXiv:2611.22219v1 Announce Type: new Abstract: Background: Generative large language models (LLMs) offer an alternative to encoder-based clinical named entity recognition (NER), but their performance on fine-grained Japanese extraction tasks and sensitivity to generation settin…

🅲 hạng C
22
Fast and Strong Image Protection against Diffusion Personalization
📄 Paper arXiv cs.CR 1 ngày trước

arXiv:2611.22494v1 Announce Type: cross Abstract: Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from s…

🅲 hạng C
21
ALIVE: Making Streaming Video Models Interactive
📄 Paper HF Daily Papers 4 ngày trước

Streaming video LLMs can continuously observe the world, yet often handle user requests in isolation. We introduce ALIVE, an interactive streaming video model supporting proactive monitoring, streaming task coordination, and feedback-seeking interaction. We construct ALIVE-SFT-28…

🅲 hạng C
21
LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complic…

🅲 hạng C
21
Safety Side Effects of Preventative Persona Steering: An Empirical Audit
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17620v1 Announce Type: new Abstract: High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference t…

🅲 hạng C
21
Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors
📄 Paper arXiv cs.AI 3 ngày trước

arXiv:2611.17846v1 Announce Type: new Abstract: Abliteration, a fine-tuning-free weight edit, removes refusal from open-weight large language models (LLMs). The developer of Arbitrary-Rank Ablation (ARA), an optimisation-based variant, reports that direction-based abliteration, …

🅲 hạng C
20
LogT: Logically Think with Images for Visual Search
📄 Paper HF Daily Papers 6 ngày trước

Thinking with images empowers vision-language models (VLMs) to use an external Zoom-in tool for fine-grained visual search. Recent works employ supervised fine-tuning (SFT) and reinforcement learning (RL) with tool-specific designs to enable such capabilities. However, achieving …

🅲 hạng C
20
Stress-Testing Sandbagging Detection Under Adaptive Attack
📄 Paper arXiv cs.CR 6 ngày trước

arXiv:2611.14950v1 Announce Type: new Abstract: Developers, auditors and researchers read evaluation scores as evidence of what a model can do. A model that sandbags, scoring low on purpose while keeping the capability, turns a low score into false reassurance. Sandbagging detec…

🅲 hạng C