News
Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
arXiv:2505.24379v3 Announce Type: replace-cross Abstract: Large Language Models are typically trained on datasets collected from...
Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation
arXiv:2512.08123v1 Announce Type: new Abstract: Language models (LMs) are often used as zero-shot or few-shot...
Unique Hard Attention: A Tale of Two Sides
arXiv:2503.14615v2 Announce Type: replace-cross Abstract: Understanding the expressive power of transformers has recently attracted attention...
Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
arXiv:2408.15176v4 Announce Type: replace-cross Abstract: We present a unified framework for automatic multitrack music arrangement...
Uni-MoE-2.0-Omni: An Open Qwen2.5-7B Based Omnimodal MoE for Text, Image, Audio and Video Understanding
How do you build one open model that can reliably understand text, images, audio and...
Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language
arXiv:2602.01451v1 Announce Type: new Abstract: Question-Answering (QA) models for low-resource languages like Bangla face challenges...
Understanding OpenAI Codex CLI Commands
We have seen a new era of agentic IDEs like Windsurf and Cursor AI...
Understanding In-context Learning of Addition via Activation Subspaces
arXiv:2505.05145v2 Announce Type: replace-cross Abstract: To perform in-context learning, language models must extract signals from...
Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models
arXiv:2602.21262v2 Announce Type: replace Abstract: With increasing integration of Large Language Models (LLMs) into areas...
Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
arXiv:2504.19254v4 Announce Type: replace Abstract: Hallucinations are a persistent problem with Large Language Models (LLMs)...
UltraCUA: A Foundation Computer-Use Agents Model that Bridges the Gap between General-Purpose GUI Agents and Specialized API-based Agents
Computer-use agents have been limited to primitives. They click, they type, they scroll. Long action...
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
arXiv:2510.25536v1 Announce Type: new Abstract: Large Language Models (LLMs) are exhibiting emergent human-like abilities and...
