AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset Paper • 2311.15308 • Published Nov 26, 2023 • 2 • 2
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning Paper • 2502.00372 • Published Feb 1 • 1 • 2
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning Paper • 2503.19263 • Published Mar 25 • 1 • 2
HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning Paper • 2403.12884 • Published Mar 19, 2024 • 1 • 2