Search papers, labs, and topics across Lattice.
Institute of Automation, Chinese Academy of Sciences
6
0
10
21
Current LLMs falter in complex rule-centered reasoning, with top models only reaching half of the potential performance on a new benchmark.
LLMs can now dynamically re-attend to procedural rules, boosting their reasoning accuracy by up to 19 points in complex scenarios.
Models fine-tuned with LongCrafter data achieve unprecedented performance on long-context tasks, particularly in high-difficulty scenarios.
Small models can outperform larger counterparts in task planning by leveraging autonomous experience exploration and hindsight training.
CoT reasoning boosts verbal reasoning but falters in visual tasks, revealing a critical gap in multimodal AI capabilities.
LLMs break in two fundamentally different ways when pushed to extreme quantization: either through gradual information loss or sudden functional breakdown of key components.
