Found 4,326 document(s)
Page 215 of 289
-
Looped Transformers offer a parameter-efficient approach to language modeling by repeatedly applying a shared backbone. Vanilla looped Transformers use each backbone output directly as the input to the next iteration. Th...
-
Looped Transformers increase computation per token by repeatedly applying a shared backbone, offering a way to improve language modeling and downstream task performance at a fixed backbone parameter count. However, each ...
-
Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying control mechanisms. Badminton racket control requ...
-
Long-horizon embodied navigation may be interrupted by a higher-priority instruction before the current task sequence is complete. The agent must finish its current atomic task, execute the inserted task, and resume the ...
-
Few-step distillation is essential for deploying modern video diffusion models. Among existing approaches, Distribution Matching Distillation (DMD) has emerged as a highly promising paradigm by achieving strong output-sp...
-
Papers in statistical theory rest on long proofs that few readers check line by line. We present KAPPA (Kit of Agents for Proof-checking Papers with a proof Assistant), open-source software that organizes language model ...
-
Knowledge graphs (KGs) provide reliable external knowledge for multi-hop factual reasoning with large language models (LLMs), yet most KGs in real-world domains such as finance and industry lack question--answer (QA) ann...
-
Efficient robotic data collection remains a major bottleneck for vision-language-action (VLA) policy learning, especially for tasks requiring accurate end-effector positioning and camera-action alignment. This challenge ...
-
JEV decision models pair a language model backbone with a lightweight scoring head to select among natural-language options. Direct selection compares candidate answers within one request, whereas entailment reranking ev...
-
As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanie...
-
Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the weaknesses are fixed. We study how to apply error-...
-
Reinforcement learning with verifiable rewards trains on cheap checks, such as unit tests, that a policy can learn to game, while a stronger check is too expensive to run on every rollout. We study how to spend a limited...
-
High-resolution video matting requires preserving fine details, such as hair strands and soft transparency, while maintaining consistency across frames. Memory-based methods achieve strong matting quality by matching cur...
-
Web-connected sensing applications continuously generate multivariate time series with evolving behavioral categories, making Time Series Class-Incremental Learning (TSCIL) essential for adapting to new classes without f...
-
Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillance routinely captures sensitive objects such as pedestrians and vehicles alongside ordinary scene co...