Submitted by korallll 41 A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models · 7 authors 8 2
Submitted by zichenwen 40 The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs · 14 authors 42 2
Submitted by yukimasano 15 Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning · 8 authors 54 2
Submitted by wzk1015 9 Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models · 12 authors 53 1
Submitted by nqbinh 7 CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models · 5 authors 3
Submitted by Holarissun 6 Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities · 2 authors 1
Submitted by Hiiamein 4 RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services · 25 authors 2
Submitted by psp-dada 3 Mitigating Object Hallucinations via Sentence-Level Early Intervention · 4 authors 5 1
Submitted by shikhar7ssu 2 OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder · 7 authors 1
Submitted by gonzmart 1 The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations · 5 authors 1
Submitted by 0xnu 1 Quantitative Risk Management in Volatile Markets with an Expectile-Based Framework for the FTSE Index · 1 authors 1