Research
On-device research index

arXiv research

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.

168,742 papers · 148 categories

Trend · papers per month

13263952 · May 202619922001200920172026
48 results for open-ended discovery

CausalEvolve improves efficiency and discovery in open-ended scientific tasks.

problem Lack of targeted guidance and knowledge organization in evolve-based agents.
method Causal scratchpad that identifies and reasons about guiding factors for evolution.
result Effective improvement in evolutionary efficiency and better solutions.

GSR optimizes tasks in scientific workflows, improving performance across diverse applications.

problem Uncertainty in task selection and evaluation in scientific workflow optimization.
method Generate-Select-Refine (GSR) framework that alternates between task generation and optimization.
result GSR outperforms existing LLM-based optimizers in various scientific applications.

A new framework evaluates LLM calibration in open-ended QA.

problem Evaluating LLM calibration in open-ended QA settings.
method Sem-ECE framework: sampling answers, grouping by semantic classes, and using frequencies as confidence.
result Sem-ECE estimators are unbiased and Sem2_2 achieves smaller calibration error.

Paper reviews intrinsic motivations and their role in open-ended learning.

problem Understanding intrinsic motivations and their role in open-ended learning.
method Defining intrinsic motivations, presenting psychological/neuroscientific and computational models.
result Links between psychological/neuroscientific and computational models of intrinsic motivations.

Study examines how decoding algorithms affect fairness in language generation models.

problem Impact of decoding algorithms on fairness in open-ended language generation.
method Systematic analysis of top-pp, top-kk, and temperature decoding algorithms.
result Decoding algorithms significantly impact fairness across demographic groups.

We consider visual domains in which a class label specifies the content of an image, and class-irrelevant properties that differentiate instances constitute the style. We present a domain-independent method that permits the open-ended recombination of style of one image with the content of another. Open ended simply me…

2018-09-28abs ↗pdf ↗

Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…

2018-05-24abs ↗pdf ↗

Quriosity analyzes curiosity-driven questions from diverse sources.

problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.

Local-HDP learns independent topics for each 3D object category in real-time.

problem Learning independent topics for each 3D object category in real-time.
method Local-Hierarchical Dirichlet Process (Local-HDP) with online variational inference.
result Local-HDP outperforms other approaches in accuracy, scalability, and memory efficiency.

Robot learns multiple tasks hierarchically by transferring knowledge.

problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.

FSPO optimizes synthetic preferences for LLM personalization.

problem Personalizing large language models for diverse users.
method FSPO reframes reward modeling as a meta-learning problem, using few labeled preferences and synthetic data.
result FSPO achieves high winrates in personalized responses, both synthetic and real.

A new approach reduces the size of prediction sets in CP, making it more efficient.

problem Large and costly prediction sets in standard CP.
method Expand correctness criterion to include inferred admissible answers, and use prediction cascades to prune implausible labels.
result Empirically effective in natural language processing and drug discovery.

A polynomial knot is a smooth embedding κ:nκ: \real \to \real^n whose components are polynomials. The case n=3n = 3 is of particular interest. It is both an object of real algebraic geometry as well as being an open ended topological knot. This paper contains basic results for these knots as well as many examples.

2006-12-28abs ↗pdf ↗

In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to frame the problem as looking for patterns that are enriched in one dataset relative to another. These pairs of datasets occur commonly, for ins…

2018-11-14abs ↗pdf ↗

Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. However, nontransitive games, such as rock-paper-scissors, can ex…

2019-01-23abs ↗pdf ↗

DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.

problem Lack of diverse training data for complex, open-ended simulators.
method Evolutionary approach using domain randomization and procedural generation.
result Successfully trains adaptive agent behavior in complex simulators.

This paper is a survey on the theory of knotoids and braidoids. Knotoids are open ended knot diagrams in surfaces and braidoids are geometric objects analogous to classical braids, forming a counterpart theory to the theory of knotoids in the plane. We survey through the fundamental notions and existing works on these …

2018-11-28abs ↗pdf ↗

Hyperfitting improves LLM generation quality by enhancing diversity, contrary to simple temperature scaling.

problem Improving open-ended generation quality of LLMs with minimal fine-tuning effort.
method Demonstrates that hyperfitting, a phenomenon where LLMs are fine-tuned to near-zero training loss, enhances generation quality and mitigates repetition.
result Hyperfitting is distinct from temperature scaling and involves a dynamic, context-dependent rank reordering mechanism in the final transformer block.

Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.

problem LLMs fall into the likelihood trap, leading to repetitive degeneration and vocabulary dullness.
method VCM reshapes the probability distribution before truncation through Contextual Searchlight and Adaptive Self-Debiasing.
result VCM mitigates the likelihood trap across open-ended generation, factual QA, and mathematical reasoning.

This paper gives mathematical models for flat knotted ribbons, and makes specific conjectures for the least length of ribbon (for a given width) needed to tie the trefoil knot and the figure eight knot. The first conjecture states that (for width one) the least length of ribbon needed to tie an open-ended trefoil knot …

2004-03-02abs ↗pdf ↗

Hallucinations in models are mislinked estimates, not errors.

problem Hallucinations in generative models as failures to link estimates to plausible causes.
method Formalized hallucinations, showed even optimal estimators hallucinate, provided a general lower bound on hallucinate rate, reframed hallucination as structural misalignment, and experimentally supported theory.
result Hallucinations are structural misalignments between loss minimization and human-acceptable outputs, leading to estimation errors.
Graphoidsmath.CO

Graphoids are topological invariants of virtual graph diagrams.

problem Understanding knotted graphs with open ends in proteins and simplifying virtual spatial graphs.
method Topological interpretations of graphoids using graph Reidemeister moves.
result Virtual graphoids are useful for studying knotted graphs and simplifying spatial graphs.

Differentiable causal discovery methods perform robustly under model violations.

problem Causal discovery algorithms struggle with real-world data due to unverifiable causal assumptions.
method Benchmarked differentiable causal discovery methods under eight model assumption violations.
result Differentiable causal discovery methods exhibit robust performance under Structural Hamming Distance and Structural Intervention Distance metrics.

Study finds Indian mutual funds adjust cash holdings based on inflows, impacting stock purchases.

problem Active liquidity management by mutual funds in India.
method Examined cash holdings and stock purchases of Indian equity mutual funds.
result Funds with active liquidity choices outperform, highlighting the importance of this strategy.

In massive open online courses (MOOCs), peer grading serves as a critical tool for scaling the grading of complex, open-ended assignments to courses with tens or hundreds of thousands of students. But despite promising initial trials, it does not always deliver accurate results compared to human experts. In this paper,…

2013-07-09abs ↗pdf ↗

New approach uses 'growth' and 'harvesting' concepts to improve deep learning models.

problem Current deep learning models lack transparency and high convergence rates.
method Reconsider neural networks as single-species population dynamics with balanced growth and harvesting rates.
result SGD with balanced growth and harvesting rates outperforms adaptive methods in all three requirements.

LDP speeds up causal discovery by partitioning, improving VAS recall and runtime.

problem Hard causal discovery in nonparametric settings with exponential complexity.
method Local Discovery by Partitioning (LDP) for causal inference around exposure-outcome pairs.
result LDP yields less biased and more precise estimates than baseline methods.

L2D-CD learns to defer expert recommendations in causal discovery.

problem Combining expert knowledge with data-driven results in causal discovery when expert recommendations may contradict data.
method Adapting learning-to-defer algorithms for pairwise causal discovery, L2D-CD learns a deferral function to select between expert recommendations and data-driven methods.
result L2D-CD outperforms both causal discovery methods and the expert used in isolation, identifying domains where the expert's performance is strong or weak.