Search papers, labs, and topics across Lattice.
6
0
10
42
State-of-the-art LLM agents face a staggering performance decline in multilingual workflows, revealing critical gaps in current evaluation methods.
Threshold-sensitive KV cache pruning is out; ReFreeKV's adaptive approach achieves robust memory efficiency without predefined limits.
Search agents face a new benchmark that evolves with real-world knowledge, challenging them to demonstrate true reasoning rather than mere fact recall.
Ditch the slow "think-first-then-translate" paradigm: ReflectMT internalizes reflection, delivering faster and better machine translation in a single pass.
Supervised fine-tuning can be dramatically improved by explicitly encouraging exploration of low-confidence data and suppressing high-confidence errors, leading to sustained gains in mathematical reasoning even after extensive RLVR training.
Text-centric image editing gets a serious upgrade with WeEdit, a 330K dataset and glyph-guided training framework that leapfrogs existing models in text clarity and instruction adherence.
