Search papers, labs, and topics across Lattice.
6
0
10
Language-action pretraining can lead to VLA policies that are not only more robust but also less dependent on visual cues, achieving up to 45% higher success rates in real-world tasks.
A unified approach to perception and planning in autonomous driving that significantly boosts robustness and performance by addressing noise-level mismatches.
Agents that thrive in stable environments can fail dramatically when faced with recoverable reliability hazards, highlighting a critical gap in current evaluation methods.
Sparse rewards can be transformed into actionable turn-level feedback, enabling agents to learn from both successful and misleading actions in long-horizon tasks.
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.
Image editing models can learn to solve visual planning puzzles with finetuning, but still lag far behind humans in zero-shot efficiency, revealing a key gap in neural visual reasoning.
