Related papers: Hey Pentti, We Did It!: A Fully Vector-Symbolic Li…
Graphical (Linear) Algebra is a family of diagrammatic languages allowing to reason about different kinds of subsets of vector spaces compositionally. It has been used to model various application domains, from signal-flow graphs to Petri…
Compiling files individually lends itself well to parallelization, but forces the compiler to operate on incomplete programs. State-of-the-art points-to analyses guarantee sound solutions only for complete programs, requiring summary…
Large Language Models (LLMs) obey consistent scaling laws -- empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these laws are descriptive rather than prescriptive: they…
We propose a call-by-value lambda calculus extended with a new construct inspired by abductive inference and motivated by the programming idioms of machine learning. Although syntactically simple the abductive construct has a complex and…
In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems, including conversational agents. Our work derives from a…
We distinguish two kinds of piecewise linear functions and provide an interesting representation for a piecewise linear function between two normed spaces. Based on such a representation, we study a fully piecewise linear vector…
We introduce MetaGlyph, a symbolic language for compressing prompts by encoding instructions as mathematical symbols rather than prose. Unlike systems requiring explicit decoding rules, MetaGlyph uses symbols like $\in$ (membership) and…
Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while…
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich…
Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic. However, these vector space representations (created through large-scale…
Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal receptive field that processes the raw pixels depicting the lips or faces. At the…
We present a symbolic transition system and bisimulation equivalence for psi-calculi, and show that it is fully abstract with respect to bisimulation congruence in the non-symbolic semantics. A psi-calculus is an extension of the…
Lattices of compatibly embedded finite fields are useful in computer algebra systems for managing many extensions of a finite field $\mathbb{F}_p$ at once. They can also be used to represent the algebraic closure $\bar{\mathbb{F}}_p$, and…
Jackendoff (2002) posed four challenges that linguistic combinatoriality and rules of language present to theories of brain function. The essence of these problems is the question of how to neurally instantiate the rapid construction and…
The notion of Reactive Turing machine (RTM) was proposed as an orthogonal extension of Turing machines with interaction. RTMs are used to define the notion of executable transition system in the same way as Turing machines are used to…
Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…
We present two rewriting systems that define labelled explicit substitution lambda-calculi. Our work is motivated by the close correspondence between Levy's labelled lambda-calculus and paths in proof-nets, which played an important role in…
Lipreading is a challenging cross-modal task that aims to convert visual lip movements into spoken text. Existing lipreading methods often extract visual features that include speaker-specific lip attributes (e.g., shape, color, texture),…
Unfoldings are a well known partial-order semantics of P/T Petri nets that can be applied to various model checking or verification problems. For high-level Petri nets, the so-called symbolic unfolding generalizes this notion. A complete…
Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or…