Submitted by PierreColombo 63 SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain · 10 authors 2
Submitted by Soontosh 58 Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification · 1 authors 9
Submitted by IAMJB 56 SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages · 12 authors 6
Submitted by akhaliq 49 FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention · 4 authors 2
Submitted by Jinghuan 47 Theia: Distilling Diverse Vision Foundation Models for Robot Learning · 7 authors 3
Submitted by akhaliq 40 MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains · 24 authors 4
Submitted by akhaliq 36 Mixture of Nested Experts: Adaptive Processing of Visual Tokens · 8 authors 4
Submitted by Tianduo 32 Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning · 3 authors 4
Submitted by akhaliq 26 Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle · 8 authors 2
Submitted by akhaliq 23 Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models · 9 authors 2
Submitted by IAMJB 21 ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation · 2 authors 1
Submitted by radi-cho 20 ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning · 2 authors 2
Submitted by sainbar 20 Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge · 8 authors 2
Submitted by IAMJB 12 Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models · 3 authors 1
Submitted by akhaliq 12 Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture · 5 authors 1
Submitted by akhaliq 12 WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds · 4 authors 2
Submitted by c-juhwan 11 VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks · 5 authors 3
Submitted by HYeungLee 11 TAPTRv2: Attention-based Position Update Improves Tracking Any Point · 8 authors 4