Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant a...
详细信息
Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant architectures. Recent works have found an empirical benefit to using probabilistic frames instead, which learn weighted distributions over group elements. In this work, we provide strong theoretical justification for this phenomenon: for commonly-used groups, there is no efficiently computable choice of frame that preserves continuity of the function being averaged. In other words, unweighted frame-averaging can turn a smooth, non-symmetric function into a discontinuous, symmetric function. To address this fundamental robustness problem, we formally define and construct weighted frames, which provably preserve continuity, and demonstrate their utility by constructing efficient and continuous weighted frames for the actions of SO(d), O(d), and Sn on point clouds. Copyright 2024 by the author(s)
For communications subject to correlated channel effects, noise recycling has recently been shown to enhance channel capacity with receiver-side-only changes. Using a taped-out chip, in a hard-detection scenario with ...
详细信息
We show how the combination of dispersive outcoupling and Kerr nonlinearity in semiconductor lasers creates regimes of self-pulsing and intensity-squeezed states of light from optical to terahertz wavelengths. CLEO 20...
详细信息
Aside from pure intellectual interest, why do we teach our students parallel computing? Most people would agree that the primary goal is to produce greater application performance. Yet students frequently parallelize ...
ISBN:
(数字)9798350364606
ISBN:
(纸本)9798350364613
Aside from pure intellectual interest, why do we teach our students parallel computing? Most people would agree that the primary goal is to produce greater application performance. Yet students frequently parallelize code only to discover that it runs disappointingly slower because they don't understand performance. To exploit parallelism effectively, it must operate synergistically with a host of other techniques, including caching, vectorization, algorithms, bit tricks, loop unrolling, using compiler switches, tailoring code to the architecture, exploiting sparsity, changing data representation, metaprogramming, etc. Software performance engineering, which encompasses these techniques, is the science and art of making code run fast or otherwise limiting its consumption of resources, such as energy, memory footprint, network utilization, response time, etc. In this talk, I will argue that the end of Moore's Law makes software performance engineering a critical skill for our students to learn.
We show how engineering a multimode nonlinear cavity with cascaded three wave mixing processes creates significant intracavity and output amplitude noise squeezing over 10 dB below the shot noise limit for multiple fr...
详细信息
We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-...
详细信息
We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional applications, calibrating LLMs is uniquely challenging. These challenges stem as much from the severe computational requirements of LLMs as from their versatility, which allows them to be applied to diverse tasks. Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs. THERMOMETER learns an auxiliary model, given data from multiple tasks, for calibrating a LLM. It is computationally efficient, preserves the accuracy of the LLM, and produces better-calibrated responses for new tasks. Extensive empirical evaluations across various benchmarks demonstrate the effectiveness of the proposed method. Copyright 2024 by the author(s)
What is the power of constant-depth circuits with MODm gates, that can count modulo m? Can they efficiently compute MAJORITY and other symmetric functions? When m is a constant prime power, the answer is well understo...
详细信息
Visual representations become progressively more abstract along the cortical hierarchy. These abstract representations define notions like objects and shapes, but at the cost of spatial specificity. By contrast, low-l...
The growing significance of RNA engineering in diverse biological applications has spurred interest in developing AI methods for structure-based RNA design. While diffusion models have excelled in protein design, adap...
详细信息
The growing significance of RNA engineering in diverse biological applications has spurred interest in developing AI methods for structure-based RNA design. While diffusion models have excelled in protein design, adapting them for RNA presents new challenges due to RNA's conformational flexibility and the computational cost of fine-tuning large structure prediction models. To this end, we propose RNAFlow, a flow matching model for protein-conditioned RNA sequence-structure design. Its denoising network integrates an RNA inverse folding model and a pre-trained RosettaFold2NA network for generation of RNA sequences and structures. The integration of inverse folding in the structure denoising process allows us to simplify training by fixing the structure prediction network. We further enhance the inverse folding model by conditioning it on inferred conformational ensembles to model dynamic RNA conformations. Evaluation on protein-conditioned RNA structure and sequence generation tasks demonstrates RNAFlow's advantage over existing RNA design methods. Copyright 2024 by the author(s)
暂无评论