Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
6
0
10
7
The value of curated, capability-balanced supervision for adapting general language models to educational tasks spanning problem solving, curriculum understanding, and instructional support is demonstrated.
DataFlex-RL, an evaluation platform for comparing choices under a common GRPO recipe, is introduced, finding that changing the data policy measurably changes the training process but does not produce a reproducible improvement over uniform training.
VeCAS achieves a 41.4% reduction in robotic navigation time, positioning itself as a game-changing "meta contrast agent" for vascular interventions.
Explicitly incorporating contact priors into visuo-tactile policies can boost manipulation success rates by over 21% in real-world scenarios.
Agents excel at selecting knowledge sources but struggle with actual task completion, achieving only 56.1-75.3% accuracy in answers despite near-perfect routing.
DataFlex makes data-centric LLM training dramatically easier, unifying disparate methods for data selection, mixing, and reweighting into a single, efficient, and reproducible framework.