Skip to content

Author

Dinesh Manocha

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

ASSEMBLE: Atomic Skills for Evidence-Grounded Video Reasoning

Results show that explicit evidence grounding can be integrated directly into long-video reasoning without sacrificing answer accuracy, and structured skill inference improves Grounded accuracy over free-form reasoning.

Xi-Yang Wu, Zong-Xia Li, Sheng Zhang et al. · 0 citations

FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex Speech

DF-VAD is introduced, an ASR-free streaming endpointer that maps bounded causal audio windows directly to Continue/Stop decisions and outperforms strong streaming and non-streaming semantic turn classifiers, and achieves the highest EOT recall among qualifying systems on TurnBench dev set $0.853.

Puneet Mathur, Dinesh Manocha · 0 citations

DRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams

The DRAGON dataset contains 11,664 annotated question instances from six diagram QA datasets, with a 2,445-instance test set carrying human-verified evidence annotations and a standardized evaluation framework, which supports future research on models that ground their predictions in visual evidence.

Anirudh Iyengar, Tampu Ravi Kumar, Gaurav Najpande et al. · 0 citations
#artificial intelligence Preprint Sep 2026

APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction

Full-duplex voice agents can now listen, speak, use tools, and act during spoken interactions, but fluent dialogue does not guarantee correct completion of delegated professional workflows. We introduce APEX-Voice, a benchmark of 120 interactive professional workflows spanning ten work archetypes such as form completio...

Puneet Mathur, Dinesh Manocha · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.