Submitted by amstrongzyf 59 UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models · 13 authors 2
Submitted by hyungjoochae 42 Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation · 9 authors 2
Submitted by BaiqiL 37 NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples · 10 authors 4
Submitted by BryanW 37 MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models · 8 authors 7
Submitted by whlzy 24 FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model · 6 authors 3
Submitted by akhaliq 22 Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities · 2 authors 2
Submitted by akhaliq 17 HART: Efficient Visual Generation with Hybrid Autoregressive Transformer · 10 authors 2
Submitted by zhoutianyi 17 Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion · 3 authors 3
Submitted by Hanbo-Cheng 12 DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation · 8 authors 2
Submitted by andriygav 11 Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts · 4 authors 5
Submitted by SyedAbdul 8 SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments · 3 authors 3
Submitted by haoosz 8 BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities · 8 authors 2
Submitted by thejaminator 8 Looking Inward: Language Models Can Learn About Themselves by Introspection · 9 authors 11
Submitted by paulgavrikov 5 How Do Training Methods Influence the Utilization of Vision Models? · 4 authors 2
Submitted by kardosdrur 5 Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Media · 4 authors 3
Submitted by yokey 4 A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement · 6 authors 2
Submitted by lixiaochuan2020 3 Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning · 3 authors 2