Found 722 document(s)
Page 7 of 49
-
Here, we present TOX-FM, a family of non-clinical PFMs trained on large-scale diverse histopathology datasets of over one million whole slide images consisting of over 60 organs across six animal species from over 14,000...
-
LLM trading agents are evaluated almost exclusively in backtests and autonomous benchmark harnesses. Deployment, where actions are irreversible, raises a different question: who verifies the agent's actions, and which fa...
-
A cover song re-renders an existing piece, most commonly by preserving its tonal content -- melody and chord progression -- while reshaping other musical attributes. This suggests a natural formulation for generative cov...
-
Benchmark compression reduces evaluation cost by selecting a small set of samples. Existing methods typically guide selection using a single metric, although benchmarks often assess models along multiple dimensions. We f...
-
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment available for solving a task,...
-
In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the field has yet to reach consensus on its definition...
-
Existing world models can generate action-conditioned video from a single image. Many focus on camera movement, allowing users to explore the generated scene. However, navigation alone does not ensure that an action foll...
-
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of mem...
-
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As...
-
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret underspecified requ...
-
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are optimal in the simula...
-
Multimodal question answering (MMQA) is based on integrating heterogeneous data sources, selectively leveraging relevant modalities, and ignoring distractors. Existing approaches based on Multimodal Large Language Models...
-
We give a short-description decomposition of bounded-width CNFs. For every fixed $\varepsilon>0$, every width-$b$ CNF on $m$ variables is an exact disjoint union of at most $2^{\varepsilon m}$ width-$b$ CNFs, each determ...
-
Hallucination stress tests can yield similar average scores across language models even when different prompts elicit hallucinations in each model. We develop a procedure that iteratively edits source-grounded seed promp...
-
DrugCLIP places small molecules and protein pockets in one space, turning genome-wide drug discovery into large-K retrieval by vector proximity. A campaign fixes over 20K pockets in advance for one library of over 500M m...