Search papers, labs, and topics across Lattice.
13
0
15
7
Intern-S2-Preview-397B not only excels in multimodal scientific reasoning but also enhances biological instruction performance without altering its foundational architecture.
Achieving 93.02% accuracy in molecular structure recognition, MinerU.Chem outperforms existing systems, unlocking new possibilities for AI-driven chemistry research.
PI-Mem achieves unprecedented long-context reasoning capabilities, outperforming traditional methods while accelerating inference by over 6 times.
SciReasoner achieves a remarkable 31% improvement in Cellular Component annotation for low-homology proteins, showcasing the power of structural reasoning in AI.
A unified definition of world models could catalyze breakthroughs across AI subfields by clarifying what these internal simulators should predict and how they should be constructed.
By preserving the semantics of pretrained models while achieving superior compositional generalization, InternVLA-A1.5 redefines how robots can learn and execute complex tasks.
Achieving trillion-parameter performance with just 35 billion parameters by scaling agent horizons reveals a new frontier in model efficiency.
Current T2I models fall short in scientific reasoning, but fine-tuning on the new SciIR dataset boosts performance by over 20%.
AI coding agents excel at translating scientific tasks into familiar formats but struggle to achieve true scientific discovery, with only 17.8% surpassing state-of-the-art benchmarks.
CUAs can achieve a 73.7% success rate on complex macOS tasks, but the secret to their performance lies in skill libraries, not just framework design.
Current models struggle with hybrid interface tasks, achieving only a 41.2% success rate, underscoring a critical gap in CUA evaluation.
Draft-OPD accelerates inference by over 5x while improving speculative decoding accuracy, transforming how draft models learn from target feedback.
Decomposing GUI agent trajectories into verifiable milestones and auditing the evidence chain yields a 10% boost in RL training performance, outperforming single-judge reward systems.
