Search papers, labs, and topics across Lattice.
Stop rewarding all LLM-generated candidates equally: ShapE-GRPO uses Shapley values to fairly distribute credit within sets, leading to better training and faster convergence.
Watch out, human scientists: autonomous agents are now coordinating distributed scientific discovery through emergent artifact exchange, potentially accelerating research across domains.
Forget hand-engineered features: LLMs can automatically generate rubrics that transform raw text into powerful representations, outperforming even pre-trained clinical models on EHR tasks.
Zero-shot robotic manipulation is now within reach: TiPToP matches a 350-hour fine-tuned model without *any* robot data.
Building a complete web application from scratch remains a surprisingly hard task for even the best AI models, with top performance at only 58% accuracy on a new end-to-end benchmark.
LLMs that ace static code-fixing benchmarks may still struggle to maintain code quality over the long, iterative haul of real-world software development.
NeuroSkill(tm) offers real-time, edge-based human-AI interaction by directly modeling human state of mind from BCI data, enabling more nuanced and empathetic agentic responses.
Standard winrate metrics in LLM evaluation can backfire, incentivizing model creators to produce homogenous models that actually *decrease* overall consumer welfare.
Agentic AI can automate complex optical systems control with near-perfect success rates, leaving code-generation approaches in the dust.
Control hybrid rigid-soft robots with the ease of AR teleoperation, thanks to a new pipeline that accurately models the soft robot's real-world behavior in simulation.
VLMs are nowhere near human-level general intelligence: they score less than 10% of human performance across a diverse set of human-designed games, especially struggling with world-model learning, memory, and planning.
LLMs can now generate complex, physically plausible 3D scenes for robotics simulation by iteratively proposing assets and refining arrangements based on physics engine feedback.
GPT-5's real-time router learns to route queries to specialized models, making it faster and more useful than its predecessors.
Open-weight reasoning models now rival proprietary systems in agentic capabilities and benchmark performance, thanks to gpt-oss-120b and gpt-oss-20b.
