Found 2,475 document(s)
Page 61 of 165
-
Localized AI manipulations in long-form videos often affect brief events within otherwise authentic content, making video-level classification insufficient for forensic analysis. Existing audio-visual deepfake benchmarks...
-
Recent DETR-based tiny object detectors adopt dynamic query mechanisms to handle severe density imbalance. However, existing designs entangle two effects: how many and which queries are decoded. This entanglement obscure...
-
Artificial intelligence is moving from one-off perception and generation tasks toward long-term planning, tool use, and interaction with real environments. Greater task competence, however, does not automatically yield a...
-
Web platforms run on multivariate time series, from service telemetry and Web traffic logs to sensor streams served through Web APIs. Yet, retention policies often archive them at coarse granularity to save storage and b...
-
Learning visual design is essential for prompt enhancement (PE) to turn underspecified user requests into coherent visual specifications for text-to-image (T2I) generation. Existing methods preserve user intent and impro...
-
Temporal Knowledge Graph (TKG) extrapolation aims to predict future facts from observed historical events. Existing methods usually achieve this goal by jointly modeling local historical evolution and long-range historic...
-
Dexterous manipulation requires high-dimensional control policies to accomplish complex contact-rich tasks while simultaneously satisfying multiple safety requirements, such as joint limits, unsafe finger configurations,...
-
Robots can use historical observations to answer spatiotemporal queries in familiar environments, but the presence of relevant evidence does not imply that existing tools support the operations a task requires. We introd...
-
LLM-powered agents increasingly rely on third-party skills that combine natural-language instructions with executable code, creating supply-chain risks that may span both artifacts. Existing skill scanners often rely on ...
-
Dexterous manipulation requires robots to leverage existing datasets for rapid skill acquisition while maintaining safety during real-world deployment to prevent damage to the robot or its surroundings. Offline-to-online...
-
Large language model (LLM) serving relies on batching to improve inference throughput, but the key-value (KV) cache grows with sequence length and limits GPU-resident concurrency. CPU offloading can expand KV capacity us...
-
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments documented in Office Actions ...
-
Automotive millimeter-wave (mmWave) radar has attracted increasing attention for semantic segmentation in autonomous driving, owing to its robustness under adverse weather and lighting conditions. Recent works have intro...
-
LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes instead of the real-world bug-introducing commits. In this pap...
-
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained primarily to maximiz...