Lattice AI Research

Research focus

Eval Frameworks & Benchmarks (1)Reasoning & Chain-of-Thought (1)Speech & Audio (1)Multimodal Models (1)

Frequent co-authors

Apoorva Kulkarni (1)Kaousheik Jayakumar (1)Sreyan Ghosh (1)Sarah Wiegreffe (1)

Papers (2)

Jun 16, 2026

3d ago

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models

LALMs can boost their temporal reasoning accuracy by 3.2% simply by better redistributing attention across audio tokens rather than relying on textual cues.

Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh +3

Eval Frameworks & Benchmarks Reasoning & Chain-of-Thought Speech & Audio

3d ago

VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision

Video-derived geometric supervision enables a 33% reduction in collisions and a 150% increase in navigation success for VLAs, reshaping the landscape of obstacle-aware navigation.

Gershom Seneviratne, Yohan Abeysinghe, Jianyu An +2

Multimodal Models Robotics & Embodied AI

Dinesh Manocha

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

Dinesh Manocha

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)