For reliable deployment, multimodal large language models (MLLMs) should recognize when an image provides insufficient evidence to answer a question and withhold unsupported answers. Yet refusal alone is not necessarily evidence of such recognition: models may refuse because of unrelated safety constraints or without i...
Ananth K. Suresh, Aveen Dayal, K. Gouthaman et al.· 0 citations
Audible World Models is introduced, a training-free framework that incorporates sound into the generated world state and maintains persistent source locations while adapting the rendered audio to changes in listener viewpoint and motion.
Duo-Wen Chen, Jin-Jin He, K. Gouthaman et al.· 0 citations
Across five 5.1-channel test sets, FGAtt achieves the strongest over- all performance, demonstrating the effectiveness of feature-level adaptation for reusing pretrained perceptual knowledge for multichannel spatial audio.
K. Gouthaman, S. Gehlot, Vishnu Raj et al.· 0 citations
VIBE is introduced, a novel text-and-video-to-music (T+V2M) generation model that leverages a depth-wise cross-layer conditioning mechanism that dynamically bridges the planning and diffusion refinement heads and a comprehensive reward modeling taxonomy, optimizing for both hard, verifiable constraints and soft, subjec...
