Found 247,085 document(s)
Page 95 of 16473
-
3D Gaussian Splatting has made high-fidelity 3D reconstruction fast and accessible, yet existing representations assume a static world. This assumption breaks down in casual captures, where a user naturally interacts wit...
-
Fairness in conformal prediction is often pursued through Mondrian calibration, which provides finite-sample coverage guarantees separately across groups. These guarantees, however, are coarse: substantial disparities ca...
-
Grounding-based open-vocabulary detectors provide a widely used framework for text-conditioned localization, with a phrase-grounding formulation that aligns object queries to individual text tokens and recovers class sco...
-
On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multi...
-
Small Language Models with quantisation and parameter-efficient adaptation are widely offered as the route to multilingual AI under compute constraints, and their efficiency is almost always reported as a single memory f...
-
Large language models (LLMs) are increasingly deployed as autonomous agents in non-verifiable domains such as financial services, where they must interpret user intent, rewrite queries, and retrieve information under dom...
-
In this paper, we introduce an Abaqus user-subroutine implementation of the phase-field model of fracture initiated by Kumar, Francfort, and Lopez-Pamies (\emph{J. Mech. Phys. Solids} 112, 523--551, 2018). The implementa...
-
Enterprise documents such as financial reports are increasingly processed by automated systems, yet they are primarily designed for human reading and exhibit complex visual structure, combining dense text with tables, ch...
-
An event camera emits events at a rate given by the scene motion, object texture, illumination, its own contrast thresholds, and other settings. Across the N-Caltech101 dataset, recorded by a single event camera, the eve...
-
Large Language Model (LLM) agents are vulnerable to adversarial inputs that induce attacker-specified malicious behaviors, commonly referred to as jailbreaking. Existing optimization-based jailbreak attacks primarily emp...
-
Most long-horizon forecasters emit the complete future in one pass. We ask whether a compact operator can instead be reused to emit contiguous future blocks, trading stored parameters for sequential computation. Recursiv...
-
Wheeled planetary rovers immobilised in loose regolith have no principled recovery controller: scripted maneuvers are terrain-specific, and naive driving deepens entrapment. We introduce a recurrent policy that learns to...
-
Pretrained diffusion models provide powerful priors for generating new materials, including inorganic crystals, but generating useful materials requires satisfying specific chemical and physical properties, from mechanic...
-
We describe a GPU-resident runtime system, HEL, built on stateful services that persist throughout the lifespan of a user application. A HEL programmer expresses a workload as an application that spawns coroutine-like ta...
-
Despite advancements in visible-thermal face recognition, where thermal probe (query) face images are matched against visible enrollment templates, existing benchmarks are currently limited by small gallery sizes (N $\ap...