Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
Small proxy models can reveal near-optimal SFT-RL budget allocations for large LLMs, streamlining the post-training process significantly.
Agents falter in partially observable settings, revealing that merely gathering visual evidence isn't enough without robust perceptual state management.
Multilingual and multimodal audio understanding is critically under-evaluated, with EXAM$^2$ revealing up to 21.7% performance gaps in current models.
