Search papers, labs, and topics across Lattice.
Beihang University;, Shenzhen Intelligent Strong Technology Co.,Ltd.
6
12
11
19
Agentic reasoning tools struggle with complex financial documents, revealing substantial performance gaps that could impact decision-making in finance.
Current LLMs struggle with cross-scenario summarization, revealing critical gaps in their reasoning capabilities and adaptability.
Achieve zero-shot cross-embodiment visual tracking by dynamically adapting control policies to inferred embodiment constraints, eliminating the need for per-robot training.
Industrial code generation gets a reasoning boost: InCoder-32B-Thinking leverages error-driven feedback and a code world model to achieve top-tier performance on complex hardware-aware tasks.
A new 32B code LLM trained specifically for industrial tasks crushes existing models on specialized domains like chip design and GPU kernel optimization, while remaining competitive on general coding benchmarks.
LLMs still struggle to consistently follow instructions when generating code, as revealed by the new CodeIF benchmark spanning function synthesis to code explanation.
