SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel ...
Sep 18, 2025 · Framing the geometric inaccuracy—specifically, the tendency for surfels to overfit to the image plane—as an aliasing problem caused by the spatial frequency of primitives …
EvoTest: Evolutionary Test-Time Learning for Self-Improving …
Sep 16, 2025 · A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like “clever but clueless interns” in novel …
CLEVER: A Curated Benchmark for Formally Verified Code …
Jul 8, 2025 · TL;DR: We introduce CLEVER, a hand-curated benchmark for verified code generation in Lean. It requires full formal specs and proofs. No few-shot method solves all stages, making …
Submissions | OpenReview
Jan 22, 2025 · Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers Lorenzo Pacchiardi, Marko Tesic, Lucy G Cheke, Jose Hernandez-Orallo 27 …
BiomedParse-V : Scaling Foundation Model for Universal
Aug 8, 2025 · Three-dimensional (3D) image segmentation plays a pivotal role in clinical diagnosis, therapy planning, and drug discovery by enabling the precise delineation of …
It is Hard to Unlearn Dogged Backdoor Samples in Diffusion Models
Sep 29, 2025 · Machine unlearning has emerged as a critical mechanism for enforcing privacy and security regulations by allowing the selective removal of training data from machine …
Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape
Sep 26, 2024 · TL;DR: We propose Flat-LoRA that aims to optimize the sharpness of the loss landscape for low-rank adaptation using efficient random weight perturbation.
STAIR: Improving Safety Alignment with Introspective Reasoning
May 1, 2025 · One common approach is training models to refuse unsafe queries, but this strategy can be vulnerable to clever prompts, often referred to as jailbreak attacks, which can …
Evaluating the Robustness of Neural Networks: An Extreme Value...
Feb 15, 2018 · Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork Robustness. The proposed CLEVER score is attack …
Contrastive Learning Via Equivariant Representation - OpenReview
Sep 25, 2024 · In this paper, we revisit the roles of augmentation strategies and equivariance in improving CL's efficacy. We propose CLeVER (Contrastive Learning Via Equivariant …
Skip to content