Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models Paper • 2512.00590 • Published Nov 29, 2025 • 45
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms Paper • 2511.17592 • Published Nov 17, 2025 • 118
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19, 2025 • 227
Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization Paper • 2510.25616 • Published Oct 29, 2025 • 95
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs Paper • 2510.11288 • Published Oct 13, 2025 • 48
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA Paper • 2510.04849 • Published Oct 6, 2025 • 114
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs Paper • 2508.11383 • Published Aug 15, 2025 • 41
HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds Paper • 2508.12782 • Published Aug 18, 2025 • 25
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens Paper • 2508.05305 • Published Aug 7, 2025 • 46
nablaNABLA: Neighborhood Adaptive Block-Level Attention Paper • 2507.13546 • Published Jul 17, 2025 • 124
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published Jul 8, 2025 • 119
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback Paper • 2507.02321 • Published Jul 3, 2025 • 39
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models Paper • 2506.19103 • Published Jun 23, 2025 • 42
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models Paper • 2506.06395 • Published Jun 5, 2025 • 133
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models Paper • 2506.06751 • Published Jun 7, 2025 • 71
ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models Paper • 2505.22569 • Published May 28, 2025 • 56
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA Paper • 2505.21115 • Published May 27, 2025 • 140
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Paper • 2506.05229 • Published Jun 5, 2025 • 38
AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment Paper • 2506.04089 • Published Jun 4, 2025 • 47