Search papers, labs, and topics across Lattice.
13
0
14
0
A training-free multi-agent system for UAV image understanding not only surpasses leading models in accuracy but also addresses fundamental reasoning failures in MLLM applications.
Conventional models of technical debt miss the dynamic, emergent behaviors of agentic AI, leading to new vulnerabilities in autonomous systems.
LLMs can misinterpret derived measurements as direct facts, leading to critical errors that can be mitigated with a novel privileged distillation approach.
Skill-SP not only pushes the performance ceiling of LLMs but also transforms initially misaligned models into high-performing agents through dynamic skill evolution.
RoboTacDex reveals that a diverse dataset of 6,000 trajectories can significantly improve humanoid robot manipulation across complex tasks.
Trajectories with higher generation confidence in VLAs can drive self-improvement without external rewards, leading to performance on par with oracle RL methods.
CausalMem achieves over 20x visual token compression while maintaining high accuracy in streaming video understanding, redefining memory efficiency in MLLMs.
AdaQ enables MLLMs to achieve superior long video understanding with just 64 frames, outperforming state-of-the-art methods by a striking margin.
Token-oriented inference optimizations can cut production costs and boost efficiency, transforming large model services from merely callable to fully operable.
BCL achieves significant and consistent performance boosts in information extraction tasks, leveraging Bayesian updates to refine label representations systematically.
Achieve real-time, proactive video understanding with StreamOV, which uses bounded memory and a novel response trigger to overcome the limitations of offline methods.
A 440MB multilingual translation model now rivals commercial APIs, opening the door for performant on-device translation.
Video-MLLMs struggle to integrate evidence across frames in document videos, especially for tasks like cross-document validation, revealing a critical gap in their ability to reason about authenticity and prevent fraud.
