Search papers, labs, and topics across Lattice.
Silent policy violations in tool-using LLMs can be mitigated by deterministic gates, improving success rates by over 12 percentage points in critical tasks.
LLM-driven program synthesis can automate EEG feature engineering while ensuring interpretability and high detection accuracy.
Nearly 80% of AI-generated pull requests are submitted concurrently, raising critical questions about collaboration efficiency and merge conflicts in AI coding agents.
Projected reads in PatchOptic not only cut token costs but also ensure that local updates remain valid in the context of shared-state workflows.
Balancing productivity and stability reveals that stronger synchronization can paradoxically increase systemic fragility in multi-agent systems.
Trajectory mining reveals skill structures but fails to translate these insights into meaningful performance gains for downstream policies.
Retaining visual figures in skill artifacts boosts CUA performance by over 23 points, proving that seeing is believing in agent training.
Current AI agents excel in structured tasks but falter at generating novel insights and tackling open-ended scientific challenges.
Even state-of-the-art multimodal models struggle with reliability in clinical tool use, revealing critical gaps in AI agent performance.
SeClaw reveals that existing benchmarks fall short in capturing the complexities of agent behavior, enabling a more nuanced evaluation of security risks in autonomous systems.
Coordinating AI agents across scientific disciplines only boosts performance when each discipline captures a unique piece of the puzzle, otherwise, simpler combined summaries often suffice.
LLMs trained with Vector Policy Optimization (VPO) learn to produce diverse solutions that unlock previously unsolvable problems in evolutionary search, outperforming models optimized for single scalar rewards.
Imagine a workspace that subtly shifts lighting and sound to match your mood, all powered by an LLM that understands your needs – this paper explores the potential and pitfalls of that reality.
Imagine slashing the human effort needed to go from hypothesis to submission-ready ML theory paper by orders of magnitude.
Uncover the hidden assumptions baked into LLM responses with a new interactive system that lets you explore alternative conceptual framings and values.
Multi-agent systems can find 5x more real-world events in satellite imagery than traditional methods, unlocking a wealth of training data for multi-temporal change detection.
Organizational AI's biggest bottleneck isn't finding the right information, but knowing what's actually true, agreed upon, or even known at all.
Gaze-tracking unlocks a new level of personalized AI assistance, enabling LLMs to infer user cognitive states and boost recall performance.
Forget brute-force scaling: crafting the *right* context from past experiences unlocks surprisingly large gains in LLM agent performance.
LLM agent skills, despite their promise, often fail in realistic settings, with performance plummeting to no-skill baselines when agents must retrieve skills from a large, uncurated collection.
LLM agents can autonomously outperform fixed evolutionary search by 3-10x on open-ended discovery tasks when given persistent memory, asynchronous collaboration, and heartbeat-based interventions.
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.
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.
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.
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.
