搜索结果：come

Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-training, they frequently suffer from knowledge conflicts, where outdated information interferes with new knowledge. In this work, we propose Conflict-free Model Editing (CoME), a novel framework that enhances the accuracy of knowledge updates in LLMs by selectively removing outdated knowledge. CoME leverages unlearning to mitigate knowledge interference, allowing new information to be integrated without compromising relevant linguistic features. Through experiments on GPT-J and LLaMA-3 using Counterfact and ZsRE datasets, we demonstrate that CoME improves both editing accuracy and model reliability when applied to existing editing methods. Our results highlight that the targeted removal of outdated knowledge is crucial for enhancing model editing effectiveness and maintaining the model's generative performance.

World models are critical for autonomous driving to simulate environmental dynamics and generate synthetic data. Existing methods struggle to disentangle ego-vehicle motion (perspective shifts) from scene evolvement (agent interactions), leading to suboptimal predictions. Instead, we propose to separate environmental changes from ego-motion by leveraging the scene-centric coordinate systems. In this paper, we introduce COME: a framework that integrates scene-centric forecasting Control into the Occupancy world ModEl. Specifically, COME first generates ego-irrelevant, spatially consistent future features through a scene-centric prediction branch, which are then converted into scene condition using a tailored ControlNet. These condition features are subsequently injected into the occupancy world model, enabling more accurate and controllable future occupancy predictions. Experimental results on the nuScenes-Occ3D dataset show that COME achieves consistent and significant improvements over state-of-the-art (SOTA) methods across diverse configurations, including different input sources (ground-truth, camera-based, fusion-based occupancy) and prediction horizons (3s and 8s). For example

Machine learning models must continuously self-adjust themselves for novel data distribution in the open world. As the predominant principle, entropy minimization (EM) has been proven to be a simple yet effective cornerstone in existing test-time adaption (TTA) methods. While unfortunately its fatal limitation (i.e., overconfidence) tends to result in model collapse. For this issue, we propose to Conservatively Minimize the Entropy (COME), which is a simple drop-in replacement of traditional EM to elegantly address the limitation. In essence, COME explicitly models the uncertainty by characterizing a Dirichlet prior distribution over model predictions during TTA. By doing so, COME naturally regularizes the model to favor conservative confidence on unreliable samples. Theoretically, we provide a preliminary analysis to reveal the ability of COME in enhancing the optimization stability by introducing a data-adaptive lower bound on the entropy. Empirically, our method achieves state-of-the-art performance on commonly used benchmarks, showing significant improvements in terms of classification accuracy and uncertainty estimation under various settings including standard, life-long and

For each smooth curve over a finite field, after puncturing it at finitely many points, we construct local systems on it of geometric origin which do not come from a family of abelian varieties. We do so by proving a criterion which must be satisfied by local systems which do come from abelian varieties, inspired by an analogous Hodge theoretic criterion in characteristic zero.

The Born Rule plays a critical role in quantum mechanics (QM) since it supplies the link between the mathematical formalism and experimental results in terms of probabilities. The Born Rule does not occur in ordinary probability theory. Where then does it come from? This has been a topic of considerable controversy in the literature. We take the approach of asking what is the simplest extension of ordinary probability theory where the Born rule appears. This is answered by showing that the Born Rule appears by adding the notion of superposition events (in addition to the ordinary discrete events) to finite probability theory. Hence the rule does not need any physics-based derivation. It is simply a feature of the mathematics of superposition when only superposition events are added to ordinary probability theory.

Specially adapted speech recognition models are necessary to handle stuttered speech. For these to be used in a targeted manner, stuttered speech must be reliably detected. Recent works have treated stuttering as a multi-class classification problem or viewed detecting each dysfluency type as an isolated task; that does not capture the nature of stuttering, where one dysfluency seldom comes alone, i.e., co-occurs with others. This work explores an approach based on a modified wav2vec 2.0 system for end-to-end stuttering detection and classification as a multi-label problem. The method is evaluated on combinations of three datasets containing English and German stuttered speech, yielding state-of-the-art results for stuttering detection on the SEP-28k-Extended dataset. Experimental results provide evidence for the transferability of features and the generalizability of the method across datasets and languages.

We study actions of higher rank lattices $Γ<G$ on hyperbolic spaces, and we show that all such actions satisfying mild properties come from the rank-one factors of $G$. In particular, all non-elementary actions on an unbounded hyperbolic space are of this type.

After nearly seven decades of excavation, the legendary ancient city of Sardis has become a UNESCO World Heritage Site, celebrating years of discoveries that continue to reshape its history。 Archaeologists say the biggest breakthroughs don't happen in a single season—they emerge as decades of evidence slowly come together

Let $κ$ be a commutative ring containing $2^{-1}$. In this paper, we prove the Comes-Kujawa's conjecture on a $κ$-basis of cyclotomic oriented Brauer-Clifford supercategory. As a by-product, we prove that the cyclotomic walled Brauer-Clifford superalgebra defined by Comes and Kujawa and ours are isomorphic if $κ$ is an algebraically closed field with characteristic not two.

Neural Style Transfer is a striking, recently-developed technique that uses neural networks to artistically redraw an image in the style of a source style image. This paper explores the use of this technique in a production setting, applying Neural Style Transfer to redraw key scenes in 'Come Swim' in the style of the impressionistic painting that inspired the film. We document how the technique can be driven within the framework of an iterative creative process to achieve a desired look, and propose a mapping of the broad parameter space to a key set of creative controls. We hope that this mapping can provide insights into priorities for future research.

Ordinary chondrites (H, L, and LL chondrites) are the most common type of meteorites comprising 80 per cent of the meteorites that fall on Earth. The source region of these meteorites in the main asteroid belt has been a basis of considerable debate in the small bodies community. L chondrites have been proposed to come from the Gefion asteroid family, based on dynamical models. We present results from our observational campaign to verify a link between the Gefion asteroid family and L chondrite meteorites. Near-infrared spectra of Gefion family asteroids (1839) Ragazza, (2373) Immo, (2386) Nikonov, (2521) Heidi, and (3860) Plovdiv were obtained at the NASA Infrared Telescope Facility (IRTF). Spectral band parameters including band centres and the band area ratio were measured from each spectrum and used to constrain the composition of these asteroids. Based on our results, we found that some members of the Gefion family have surface composition similar to that of H chondrites, primitive achondrites, and basaltic achondrites. No evidence was found for L chondrites among the Gefion family members in our small sample study. The diversity of compositional types observed in the Gefion a

We pick up the thread of $B\to Kπ$ direct CPV (DCPV) difference, linking to the 4th generation prediction (and current quest) of $t$-dependent CPV (TCPV) in $B_s \to J/ψ\,φ$. We then soar up to the heavens with possible source of CPV for the Universe (CPV-4-U); for the "cauldron" that stirs strong phase transitions, we raise the possible link between electroweak symmetry breaking and large Yukawa couplings (4-EWSB). With the prognosis for 2011, 2012 and beyond, we stress these as preview for the possible 4th generation to come: CPV-4-U and the \emph{raison d'être} for our Universe (and ourselves); 4-EWSB and the \emph{raison d'être} for the LHC itself.