Search papers, labs, and topics across Lattice.
UC Berkeley 2 UT Austin 3 Stanford University 4 Princeton University 5 Together AI
Berkeley AI Research (BAIR)7
19
10
29
Verifier-free evolution can now match or exceed the performance of verifier-based methods, while slashing API costs by 3x and boosting throughput by 10x, thanks to a clever model orchestration strategy.
K-means, previously relegated to offline processing, gets a 17.9x speed boost on modern GPUs thanks to Flash-KMeans' clever IO and contention optimizations.
Get 2x faster video generation from diffusion transformers without sacrificing quality, thanks to a clever parameter-free error compensation technique.
Models are substantially better at pairwise self-verification than independent scoring, unlocking a more efficient and accurate approach to test-time scaling for complex reasoning.
Uncertainty-driven dynamic compute allocation lets web agents outperform naive test-time scaling by 9.1% while using 2.3x fewer tokens.
By explicitly encoding 3D geometry, GeoDrive achieves more realistic and controllable autonomous driving scene modeling, outperforming prior world models in action accuracy and spatial awareness.
Forget sparse KV caches – QuantSpec's hierarchical 4-bit quantization unlocks 2.5x speedups in long-context LLM inference with >90% acceptance rates.
