Found 2,471 document(s)
Page 16 of 165
-
Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewards can become ineffective as training progresses. We identify two failure modes...
-
Hidden randomized rounding couples the privacy loss of successive integer releases. We study a rational-feedback mechanism under predictable signed-unit participation and full observation of every physical output. A prep...
-
Binary Goppa codes are important in coding theory and cryptography. It is well-known that the minimum distance of a binary Goppa code defined by a squarefree polynomial of degree $r$ is at least $2r+1$. Though from the c...
-
Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can exploit such mixed-quality data, but only if the co...
-
As people use large language models (LLMs) over time, they develop their own ways of prompting to achieve desired results. These useful experiences often remain scattered and unorganized across conversations. Yet existin...
-
We develop a vision--radio-frequency (RF) cooperative integrated sensing and communication (ISAC) framework that jointly uses visual priors and RF observations for transmit-side beam control and receiver-side clutter sup...
-
A bimanual demonstration specifies both what the robot should do and one particular schedule for when each arm should act. Standard imitation learning does not distinguish task-required cross-arm constraints from inciden...
-
The rapid integration of power electronics converters has fundamentally altered the power grid's dynamic landscape, making modularity of operation and interoperability of heterogeneous devices two critical hurdles for po...
-
Neuro-symbolic artificial intelligence (NeSy AI) combines neural perception with symbolic reasoning, enabling logical reasoning. Hyperdimensional computing (HDC) is promising for NeSy AI, owing to its high parallelism an...
-
Vision-and-language navigation (VLN) relies on retaining and using relevant observations. Yet growing histories introduce redundancy, and retained information may remain underused. We introduce ReInsBench, a diagnostic b...
-
Wheel kinematics can support odometry for quadrupedal wheel-legged robots when LiDAR geometry provides weak motion constraints. However, slip and contact loss make rolling predictions unreliable, and contact state alone ...
-
World Action Models (WAMs) typically represent the world through latent embeddings from pretrained video models, which entangle heterogeneous aspects of the world, from how it looks (e.g., texture and color) to how it is...
-
Generating reusable driving environments requires both controllable future observations and an explicit representation that supports rendering from different viewpoints, yet existing methods still recover explicit scenes...
-
Reconstructing human activity from egocentric video requires more than recovering individual 3D components: the observer's motion, surrounding geometry, and hand-object interactions must fit together in a consistent worl...
-
Safe AC dispatch requires both feasible operating points and enough ramping capability to reach the next target. This paper constructs convex inner approximations that connect nonlinear network feasibility, constrained d...