Search papers, labs, and topics across Lattice.
50 papers published across 5 labs.
AI's role in medical education has exploded post-2021, with generative AI and learner-facing applications dominating a field now heavily concentrated in the US and a few elite institutions.
Embodied agents improve on complex tasks by recombining learned skills, but their ability to extract value from additional experience saturates, failing to scale with learning samples.
Slash LLM evaluation costs by over 270x without sacrificing accuracy, revealing that even top open-weight models struggle to outperform simple baselines on AML transaction fraud detection.
Coding agents routinely fail to build agents that truly meet user requirements, with the gap between demonstration and delivery being the norm.
Real-world professional tasks demand agents that learn from exploration and feedback, a capability unlocked by a novel engine that reconstructs environments to force agents through the full problem-solving lifecycle.
AI's role in medical education has exploded post-2021, with generative AI and learner-facing applications dominating a field now heavily concentrated in the US and a few elite institutions.
Embodied agents improve on complex tasks by recombining learned skills, but their ability to extract value from additional experience saturates, failing to scale with learning samples.
Slash LLM evaluation costs by over 270x without sacrificing accuracy, revealing that even top open-weight models struggle to outperform simple baselines on AML transaction fraud detection.
Coding agents routinely fail to build agents that truly meet user requirements, with the gap between demonstration and delivery being the norm.
Real-world professional tasks demand agents that learn from exploration and feedback, a capability unlocked by a novel engine that reconstructs environments to force agents through the full problem-solving lifecycle.
LLM agents significantly outperform numerical optimizers in four out of five black-box optimization domains, but adding more numerical tools doesn't always help.
LEGO-building AI agents can assemble physically valid structures from text prompts, but their designs lag significantly behind human creativity and complexity.
Even the best vision-language models struggle with predictive spatial reasoning, scoring less than 60% on a new benchmark designed to test anticipating unseen outcomes.
Source-side training dynamics, not just current values or training time, prospectively predict OOD degradation, even across model architectures.
Irrelevant text distractors cripple mixed-modality retrieval performance more than images, revealing a text modality preference that degrades performance in a V-shaped curve.
Even state-of-the-art LMMs struggle with reasoning-informed visual editing, with the best model only achieving 56.6% accuracy on a new comprehensive benchmark.
Most published TTA methods for time-series forecasting are outperformed by simple, hyperparameter-free baselines under realistic label delays, with some even becoming harmful.
City-scale audio-visual reasoning is currently dominated by expensive agentic pipelines, not standalone multimodal models.
QNN gate selection and arrangement, not just qubit count, critically dictate financial forecasting performance, with the best configuration outperforming classical BiLSTM and exhibiting significant noise sensitivity on current quantum hardware.
Releasing LLM watermark detectors might be safe: a split-key approach allows public detection of forgeries while keeping full forensic capabilities private.
Research reports can now be continuously updated with over 60% fewer search calls and 33% less token consumption, maintaining high quality over time.
Probes can now detect subtle, unverbalized LLM deception with near-perfect accuracy, even when the model's true intentions are hidden from external observation.
LLM test generation quality is overestimated by 30% when evaluated against single references, with a new metric revealing widespread missed behaviors and faulty assertions.
Frontier LLMs fail to reliably identify high-value training data or accurately predict performance gains, highlighting a critical gap in their self-improvement potential.
Unconditional KSDs are lifted to the conditional setting using operator-valued kernels, enabling goodness-of-fit testing for conditional models without knowing covariate distributions.
Synthetic data alone can match real-world GAD performance, but unlocking further gains requires models that explicitly fuse topological and semantic evidence.
Parameter-efficient adaptation methods can match full fine-tuning gains for tabular foundation models, while selective aggregation offers a clear path to improved predictions over ensemble averaging.
A 10x increase in AI time horizon is significantly easier for AI development in the 2-30 minute task range than for tasks outside this sweet spot.
Real-world AI agent breaches at major labs demonstrate that assumed boundaries are insufficient, demanding a shift to continuous, proactive assurance across the entire execution system.
Most 3D foundation models struggle to accurately estimate absolute metric distances, a fundamental capability overlooked by existing benchmarks.
Frontier MLLMs exhibit strong local perception but falter on long-horizon audio-visual reasoning, with a single benchmark exposing specific failure modes like identity drift and cross-modal misalignment.
LLM agents can achieve high task accuracy while exhibiting profound epistemic *im*humility, failing to acknowledge uncertainty even when presented with contradictory evidence.
Coding agent benchmarks can now dynamically scale difficulty and avoid data leakage by having agents evaluate each other, with the latest models generating tasks that defeat older solvers 10x more often.
LLMs exhibit "Thinking Inertia," stubbornly continuing to show explicit reasoning even when explicitly instructed not to, particularly in open-ended tasks.
Most clinical LLM benchmarks fail to capture the dominant documentation and knowledge retrieval tasks physicians actually use them for, rendering their scores largely irrelevant to real-world performance.
Even state-of-the-art MLLMs struggle to grasp the nuanced data interpretation and narrative coherence required for data videos, with significant performance gaps in causal reasoning and narrative structure.
A single adversarial auditor can't fool Auditopus, a decentralized LLM fairness auditing system that achieves up to 78% error reduction against fairwashing attacks.
Most recalibration methods fail to guarantee calibration for critical outcomes, but this new approach ensures predictions are trustworthy even when focusing on rare or extreme events.
Audio-language models excel at identifying sounds but fail to grasp the crucial context of how speakers react to them.
Current image generation models struggle with rendering dense, multi-region text, with fidelity dropping by over 14 points when clarity is prioritized.
Current multimodal agents can build sophisticated perception-control pipelines but fail to reliably execute physical tasks, losing object states and mistaking unfinished goals for completion.
AI agents are now building climate models that outperform published research and offer novel hypotheses for long-standing scientific debates.
Most gradient-based methods fail to reliably attribute learned behaviors in online RL, with simple fluency metrics often proving more predictive than complex attribution techniques.
Input-blind controls can account for substantial oracle headroom in adaptive computation, challenging the assumption that observed gains directly reflect the efficacy of selected layer programs.
Model selection for scientific forecasting is fundamentally protocol-dependent, with optimal choices reversing based on dataset size, system complexity, and evaluation metrics like state refresh versus closed-loop performance.
Frontier LLMs can achieve substantial recursive self-improvement, closing nearly half of the performance gap on complex benchmarks by jointly optimizing data, training, and execution harnesses within a unified, agent-native environment.
LLM safety patches can appear effective on benchmarks but cause severe collateral damage to benign behaviors, a critical flaw missed by aggregate metrics.
Most alignment model organisms degrade core capabilities and naturalness during training, undermining interpretability findings; a new multi-objective approach preserves these crucial aspects.
Current LLMs struggle to translate visual scenes into executable geometric functions, failing even basic trajectory generation tasks.
Sim racing drivers' braking and strategy behaviors are not car-interchangeable, challenging existing profiling assumptions.
Stated-preference economics offers a robust framework for evaluating LLM responses to subjective questions, revealing that even advanced models can fail basic economic validity tests.
Black-box text-to-music generators can be steered to precisely match complex user intent by an agent that iteratively refines prompts based on rubric-based audio verification.
On-policy distillation excels at teaching LLMs to *use* their existing knowledge for complex reasoning, but doesn't actually teach them *new facts*.
English skeletons offer a minor, inconsistent boost in multilingual math reasoning, with optimal language choice proving highly context-dependent.
Real-world coding agent usage reveals that task flow, not just task completion, dramatically impacts agent cost and effectiveness, suggesting current benchmarks are misaligned with user behavior.
