Generates biomedical abstracts from titles, years, and keywords.
problem Difficulties in understanding biomedical research papers due to specialized language.
method Conditional transformer-based language model with metadata conditioning.
result Generated abstracts are more relevant and non-trivial than GPT-2.
Study investigates how simple speech sounds can form abstract categories.
problem How do abstract categories like phonemes emerge from speech exposure?
method Used modeling techniques to test Memory-Based Learning and Error-Correction Learning.
result Error-Correction Learning models can learn abstractions, identifying phone inventory and grouping.
Deep learning models generate languages that lack abstract reasoning.
problem Lack of abstract reasoning in deep learning-generated languages.
method Analyzed emergent language from two multi-agent games with compositional measures.
result Deep learning solutions often fail to generalize to out-of-training examples.
Language helps RL agents learn complex tasks by composing sub-skills.
problem Solving complex, temporally-extended tasks in RL.
method Using language as an abstraction to learn and reuse sub-skills.
result Agents can learn and solve diverse, temporally-extended tasks.
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalabilit…
Automatic summarization of natural language is a current topic in computer science research and industry, studied for decades because of its usefulness across multiple domains. For example, summarization is necessary to create reviews such as this one. Research and applications have achieved some success in extractive …
Language models exhibit low-rank structure, which can be used for generation.
problem Understanding the low-dimensional structure of large language models.
method Empirical demonstration and theoretical analysis of the approximate rank of language models' logits.
result Language models can generate responses using linear combinations of unrelated prompts.
SLM models code syntax as trees to generate any programming language code.
problem Generating any piece of code in a given language without restrictions.
method Structural language modeling (SLM) decomposes code into ASTs and estimates probabilities over nodes.
result SLM model generates arbitrary code in any language, outperforming previous methods.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
Constellation learns group-level visual relationships for abstract reasoning.
problem Learning configurational properties of entire groups of objects.
method Introduces Constellation, a network that learns relational abstractions over static visual scenes.
result Offers a basis for abstract relational reasoning and sensory imagination.
Paper trains models to resist string transformations.
problem Vulnerability of NLP models to adversarial string transformations.
method Combines search and abstraction techniques for robust training.
result Trained models resist combinations of user-defined transformations.
Study develops a new algorithm for assessing clinical trial abstracts.
problem Limited tools for assessing qualitative statements in clinical research.
method Developed a three-class sentiment classification algorithm using BERT model.
result Algorithm achieved 91.3% classification accuracy and 0.92 macro F1-Score.
LLMs translate natural language trading intents into correct option strategies using a domain-specific language.
problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.
Automates translating natural language to Verilog for digital design.
problem Manual translation of natural language specifications to Verilog is time-consuming and error-prone.
method Fine-tuned GPT-2 to derive Verilog from English, using a dataset of design tasks.
result GPT-2 achieved 94.8% correct translation across simple and abstract design tasks.
Abstract cone operators prove scalar curvature comparisons on singular manifolds.
problem Proving scalar curvature inequalities on manifolds with cone singularities.
method Using index theory for twisted Dirac operators on Lipschitz bundles.
result Lipschitz rigidity for scalar curvature on odd-dimensional manifolds.
Mid-training improves RL by identifying compact action abstractions.
problem Unlocking full potential of RL with large language models.
method RA3 algorithm that optimizes sequential variational lower bound and discovers latent structures via RL.
result Improves performance by 8 points on HumanEval and 4 points on MBPP.
Study of sentence representations in AI shows parallels to human learning.
problem Understanding how AI systems learn and generalize from training data.
method Diagnostic tests, performance analysis, training distribution effects, representation changes with augmentations.
result AI systems can learn abstract rules and generalize under certain conditions, similar to human zero-shot reasoning.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
Stan is a probabilistic programming language that has been increasingly used for real-world scalable projects. However, to make practical inference possible, the language sacrifices some of its usability by adopting a block syntax, which lacks compositionality and flexible user-defined functions. Moreover, the semantic…
Word embeddings are a powerful approach for unsupervised analysis of language. Recently, Rudolph et al. (2016) developed exponential family embeddings, which cast word embeddings in a probabilistic framework. Here, we develop dynamic embeddings, building on exponential family embeddings to capture how the meanings of w…
In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and ge…
Optimus pre-trains sentences in a latent space for various NLP tasks.
problem Training large-scale language models for diverse NLP tasks.
method Pre-trained Variational Autoencoder (VAE) on large text corpus, fine-tuned for various tasks.
result Optimus achieves state-of-the-art on VAE language modeling benchmarks.
Language helps RL agents learn complex relational and causal structures.
problem Learning relational and causal structure in complex environments.
method Training RL agents to predict language descriptions and explanations.
result Language aids agents in learning challenging relational and causal tasks.
We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation. Therefore, the dev…
Ideal attribution mechanisms track model interactions for faithful watermarks.
problem Ensuring models provide transparent and fair attribution decisions.
method Introducing ideal attribution mechanisms and a ledger for tracking model interactions.
result A unified framework for evaluating watermarking schemes, clarifying attainable guarantees.
The abstract reviews financial concepts using physics.
problem Financial pricing and risk management.
method Discrete time formalism, path integral, Green's function formulas.
result Formulas for pricing and risk mitigation methods.
This work explains how linear representations in large language models arise from training objectives and gradient descent.
problem Understanding the origins of linear representations in large language models.
method A latent variable model to abstract and formalize concept dynamics, combined with analysis of the softmax cross-entropy objective and gradient descent.
result Linear representations emerge when learning from data matching the latent variable model, and this simple structure suffices to yield linear representations.
This work concludes a series of four papers on the foundational theory of orbifolds and stacks. We apply the abstract theory, developed in its predecessors, to orbifolds derived from manifolds. Specifically, we show how the very concrete topological base spaces associated to such orbifolds can be described and manipula…
The paper develops a framework for abstracting causal models using category theory.
problem Difficulties in changing the variables used to describe a system, especially from fine-grained to coarse-grained.
method Introduces a category of interventional causal models and uses enriched category theory to prove compositionality properties.
result Compositionality of model transformations is established, with bounded errors for each step.
New method uses low logit rank to simplify complex language models.
problem Understanding and learning from modern language models.
method Exploiting the low logit rank structure of language models for efficient learning.
result An efficient algorithm for learning low logit rank models from queries.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
The present paper is a review of the current state of Graph-Link Theory (graph-links are also closely related to homotopy classes of looped interlacement graphs), dealing with a generalisation of knots obtained by translating the Reidemeister moves for links into the language of intersection graphs of chord diagrams. I…
Enhanced LSTM model learns complex temporal dependencies.
problem Modeling long-term dependencies in sequential data.
method Gamma-LSTM with hierarchical memory units and gates.
result Gamma-LSTM outperforms regular and stacked LSTMs in sequence prediction.
New methods predict language model out-of-distribution behaviors using causal mechanisms.
problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.
The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine translation (NMT), have achieved state-of-the-art performance on these tasks by treating…
This paper analyzes speculative decoding, a method to speed up large language model inferences.
problem Theoretical understanding of speculative decoding is lacking.
method Conceptualizes speculative decoding as a markov chain problem and studies its key properties.
result Reveals fundamental connections between LLM components and their impact on decoding efficiency.
UQE uses LLMs to analyze unstructured data efficiently.
problem Efficient analytics on unstructured data.
method Proposes UQE, a query engine that uses LLMs to interpret UQL queries.
result Demonstrates efficient analytics on various unstructured data types.
Triangulation filters spurious circuits in multilingual models.
problem Unreliable explanations of multilingual models across languages.
method Formalizes reference families and introduces triangulation as a causal acceptance rule.
result Triangulation provides a falsifiable standard for mechanistic claims.
SuTaT creates dialogue summaries for tete-a-tetes without labeled data.
problem Lack of high-quality paired dialogue-summary data.
method Unsupervised model for tete-a-tetes, modeling customer and agent roles separately.
result SuTaT outperforms on automatic and human evaluations.
ACI converts call center conversations into actionable data.
problem Real-time spoken language understanding for call center conversations.
method Combines speech recognition, entity and intent recognition, and a business rules engine.
result ACI converts live audio into structured events for real-time supervision and assistance.
NumPyro accelerates probabilistic programming with JAX transformations.
problem Efficiently handling probabilistic models with hardware acceleration.
method Composable effects and program transformations in JAX.
result Iterative NUTS formulation JIT compiled for speed.
Machine learning reduces workload in healthcare systematic reviews by 70%.
problem Efficiently screening abstracts for systematic reviews in healthcare.
method Training SVM classifiers on labeled abstracts to classify RCTs.
result SVM classifier achieved 90% accuracy and 0.84 F1 score.
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE di…
Unified model learns concepts across domains like left and right.
problem Limited generalization of language concepts in inference-only models.
method Logic-Enhanced Foundation Model (LEFT) with a differentiable, domain-independent program executor.
result LEFT flexibly learns and reasons with concepts across 2D images, 3D scenes, human motions, and robotic manipulation.
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN),…
RL enhances LLM planning but introduces spurious solutions and diversity collapse.
problem Theoretical understanding of RL's benefits and limitations in LLM planning.
method Graph-based abstraction, policy gradient, Q-learning, supervised fine-tuning.
result RL's exploration is crucial for generalization, but PG suffers from diversity collapse.
Improved source code summarization using extended Tree-LSTM.
problem Challenges in applying LSTM to structured source code.
method Extended Tree-LSTM for abstract syntax trees (ASTs).
result Multi-way Tree-LSTM achieves better results than state-of-the-art techniques.
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens. There are many ways to estimate or learn the …