A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study analyzes carbon footprint of 1,417 ML models on Hugging Face.
FairLangProc simplifies fairness in NLP models for Python users.
A new loss function HUG decouples and generalizes neural collapse.
StableLM 2 1.6B is a new language model series with detailed evaluations and performance metrics.
NIFTY dataset for financial forecasting models.
Study builds a Japanese financial-specific LLM through continual pre-training.
Bedside monitors in Intensive Care Units (ICUs) frequently sound incorrectly, slowing response times and desensitising nurses to alarms (Chambrin, 2001), causing true alarms to be missed (Hug et al., 2011). We compare sliding window predictors with recurrent predictors to classify patient state-of-health from ICU multi…
Study evaluates ML methods for two-sample testing with right-censored data.
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
The paper evaluates integrals of planes and their relation to convex set angles.
Model learns brevity by exposing to easy problems, improving efficiency without explicit length penalties.
The paper proves inequalities for convex hypersurfaces in spheres and hyperbolic spaces.
A new Hopfield model reduces inefficiency in large transformer models.
A pretrained LLM and its finetuned version can detect OOD data effectively.
DoRA improves adaptation efficiency for large models by factoring norms and fusing kernels.
Nesterov's momentum trick is famously known for accelerating gradient descent, and has been proven useful in building fast iterative algorithms. However, in the stochastic setting, counterexamples exist and prevent Nesterov's momentum from providing similar acceleration, even if the underlying problem is convex and fin…
Given an arbitrary closed set A of , we establish the relation between the eigenvalues of the approximate differential of the spherical image map of A and the principal curvatures of A introduced by Hug-Last-Weil, thus extending a well known relation for sets of positive reach by Federer and Zaehle. The…
Optimizes master faces for 2D and 3D face verification using evolutionary algorithms and neural networks.
Face recognition systems are vulnerable to composite face reconstruction attacks.
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the inpu…
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work …
Despite the remarkable progress in face recognition related technologies, reliably recognizing faces across ages still remains a big challenge. The appearance of a human face changes substantially over time, resulting in significant intra-class variations. As opposed to current techniques for age-invariant face recogni…
In this paper, we study face vectors of simplicial posets that are the face posets of cell decompositions of topological manifolds without boundary. We characterize all possible face vectors of simplicial posets whose geometric realizations are homeomorphic to the product of spheres. As a corollary, we obtain the chara…
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …
Study on critical faces convergence in a Poisson point process.
Bayesian optimization generates personalized face stimuli for cognitive neuroscience.
Motivated principally by the low-rank matrix completion problem, we present an extension of the Frank-Wolfe method that is designed to induce near-optimal solutions on low-dimensional faces of the feasible region. This is accomplished by a new approach to generating ``in-face" directions at each iteration, as well as t…
The paper is motivated by the study of graded representations of Takiff algebras, cominuscule parabolics, and their generalizations. We study certain special subsets of the set of weights (and of their convex hull) of the generalized Verma modules (or GVM's) of a semisimple Lie algebra $\lie g$. In particular, we exten…
Formula for manifold Euler characteristic using even faces.
Face recall is a basic human cognitive process performed routinely, e.g., when meeting someone and determining if we have met that person before. Assisting a subject during face recall by suggesting candidate faces can be challenging. One of the reasons is that the search space - the face space - is quite large and lac…
New flows represent Thurston norm ball faces, differing by veering mutations.
In this paper we address the following question, given a face representation, how many identities can it resolve? In other words, what is the capacity of the face representation? A scientific basis for estimating the capacity of a given face representation will not only benefit the evaluation and comparison of differen…
Enhances 2D face recognition with 3D features using active illumination.
Paper proposes a method to encrypt faces while maintaining visual similarity.
Study evaluates the impact of academic support center's face-to-face assistance on student performance.
The face pairing graph of a 3-manifold triangulation is a 4-valent graph denoting which tetrahedron faces are identified with which others. We present a series of properties that must be satisfied by the face pairing graph of a closed minimal P^2-irreducible triangulation. In addition we present constraints upon the co…
If a convex body C has modular and irreducible face lattice (and is not strictly convex), there is a face-preserving homeomorphism from C to a section of a cone of hermitian matrices or C has dimension 8, 14 or 26.
Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-gr…
Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variatio…
We prove that each lower-dimensional face of a quasi-arithmetic Coxeter polytope, which happens to be itself a Coxeter polytope, is also quasi-arithmetic. We also provide a sufficient condition for a codimension face to be actually arithmetic, as well as a few computed examples.
New method labels GAN-generated faces without stereotyping.
Paper describes a state sum formula for a graph coloring polynomial.
Given a point (the "spider") on a rectangular box, we would like to find the minimal distance along the surface to its opposite point (the "fly" - the reflection of the spider across the center of the box). Without loss of generality, we can assume that the box has dimensions with the spider on one …
Face recognition system trained with noisy labels.
We study polar orbitopes, i.e. convex hulls of orbits of a polar representation of a compact Lie group. The face structure is studied by means of the gradient momentum map and it is shown that every face is exposed and is again a polar orbitope. Up to conjugation the faces are completely determined by the momentum poly…
The twisted face-pairing construction of our earlier papers gives an efficient way of generating, mechanically and with little effort, myriads of relatively simple face-pairing descriptions of interesting closed 3-manifolds. The corresponding description in terms of surgery, or Dehn-filling, reveals the twist construct…
The paper studies invariant convex sets in representations with nontrivial copolarity.
We call "flippable tilings" of a constant curvature surface a tiling by "black" and "white" faces, so that each edge is adjacent to two black and two white faces (one of each on each side), the black face is forward on the right side and backward on the left side, and it is possible to "flip" the tiling by pushing all …