Searcharxiv⌕ Search

arXiv subjects

Ali Abbas

Publications and source records attributed to Ali Abbas.

11 recordsLinked to original sources
arXiv2025

AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning

Generalist robot learning remains constrained by data: large-scale, diverse, and high-quality interaction data are expensive to collect in the real world. While simulation has become a promising way for scaling up data collection, the related tasks, including simulation task design, task-aware scene generation, expert demonstration synthesis, and sim-to-real transfer, still demand substantial human effort. We present AnyTask, an automated framework that pairs massively parallel GPU simulation with foundation models to design diverse manipulation tasks and synthesize robot data. We introduce three AnyTask agents for generating expert demonstrations aiming to solve as many tasks as possible: 1) ViPR, a novel task and motion planning agent with VLM-in-the-loop Parallel Refinement; 2) ViPR-Eureka, a reinforcement learning agent with generated dense rewards and LLM-guided contact sampling; 3) ViPR-RL, a hybrid planning and learning approach that jointly produces high-quality demonstrations with only sparse rewards. We train behavior cloning policies on generated data, validate them in simulation, and deploy them directly on real robot hardware. The policies generalize to novel object poses, achieving 44% average success across a suite of real-world pick-and-place, drawer opening, contact-rich pushing, and long-horizon manipulation tasks. Our project website is at https://anytask.rai-inst.com .

cs.RO↗
arXiv2025

Operator-Theoretic Framework for Gradient-Free Federated Learning

Federated learning must address heterogeneity, strict communication and computation limits, and privacy while ensuring performance. We propose an operator-theoretic framework that maps the $L^2$-optimal solution into a reproducing kernel Hilbert space (RKHS) via a forward operator, approximates it using available data, and maps back with the inverse operator, yielding a gradient-free scheme. Finite-sample bounds are derived using concentration inequalities over operator norms, and the framework identifies a data-dependent hypothesis space with guarantees on risk, error, robustness, and approximation. Within this space we design efficient kernel machines leveraging the space folding property of Kernel Affine Hull Machines. Clients transfer knowledge via a scalar space folding measure, reducing communication and enabling a simple differentially private protocol: summaries are computed from noise-perturbed data matrices in one step, avoiding per-round clipping and privacy accounting. The induced global rule requires only integer minimum and equality-comparison operations per test point, making it compatible with fully homomorphic encryption (FHE). Across four benchmarks, the gradient-free FL method with fixed encoder embeddings matches or outperforms strong gradient-based fine-tuning, with gains up to 23.7 points. In differentially private experiments, kernel smoothing mitigates accuracy loss in high-privacy regimes. The global rule admits an FHE realization using $Q \times C$ encrypted minimum and $C$ equality-comparison operations per test point, with operation-level benchmarks showing practical latencies. Overall, the framework provides provable guarantees with low communication, supports private knowledge transfer via scalar summaries, and yields an FHE-compatible prediction rule offering a mathematically grounded alternative to gradient-based federated learning under heterogeneity.

cs.LG↗
arXiv2025

Galton's Law of Mediocrity: Why Large Language Models Regress to the Mean and Fail at Creativity in Advertising

Large language models (LLMs) generate fluent text yet often default to safe, generic phrasing, raising doubts about their ability to handle creativity. We formalize this tendency as a Galton-style regression to the mean in language and evaluate it using a creativity stress test in advertising concepts. When ad ideas were simplified step by step, creative features such as metaphors, emotions, and visual cues disappeared early, while factual content remained, showing that models favor high-probability information. When asked to regenerate from simplified inputs, models produced longer outputs with lexical variety but failed to recover the depth and distinctiveness of the originals. We combined quantitative comparisons with qualitative analysis, which revealed that the regenerated texts often appeared novel but lacked true originality. Providing ad-specific cues such as metaphors, emotional hooks and visual markers improved alignment and stylistic balance, though outputs still relied on familiar tropes. Taken together, the findings show that without targeted guidance, LLMs drift towards mediocrity in creative tasks; structured signals can partially counter this tendency and point towards pathways for developing creativity-sensitive models.

cs.AI↗
arXiv2025

Exponentially weighted moving average chart using zero-inflated negative binomial distribution

Zero-inflated models are frequently used to deal with data having many zeros. A commonly used model for over-dispersed data containing zeros is known as the zero-inflated Poisson model. However, to account for the heterogeneity of counts that leads to excess variance besides inflation of zeros in the data using a more flexible model than the zero-inflated Poisson model, a zero-inflated negative binomial (ZINB) is suggested. In the present study, Shewhart and exponentially weighted moving average (EWMA) control charts are suggested to monitor the ZINB data. The charts are compared using the average run length and standard deviation of run length by using extensive Monte Carlo simulations. Besides a comprehensive simulation study assuming different settings of parameters of ZINB, a real data set is used to show the practicality of the proposed charts. The results indicate that the EWMA chart is better than the Shewhart chart.

stat.ME↗
arXiv2025

Vehicle detection from GSV imagery: Predicting travel behaviour for cycling and motorcycling using Computer Vision

Transportation influence health by shaping exposure to physical activity, air pollution and injury risk. Comparative data on cycling and motorcycling behaviours is scarce, particularly at a global scale. Street view imagery, such as Google Street View (GSV), combined with computer vision, is a valuable resource for efficiently capturing travel behaviour data. This study demonstrates a novel approach using deep learning on street view images to estimate cycling and motorcycling levels across diverse cities worldwide. We utilized data from 185 global cities. The data on mode shares of cycling and motorcycling estimated using travel surveys or censuses. We used GSV images to detect cycles and motorcycles in sampled locations, using 8000 images per city. The YOLOv4 model, fine-tuned using images from six cities, achieved a mean average precision of 89% for detecting cycles and motorcycles. A global prediction model was developed using beta regression with city-level mode shares as outcome, with log transformed explanatory variables of counts of GSV-detected images with cycles and motorcycles, while controlling for population density. We found strong correlations between GSV motorcycle counts and motorcycle mode share (0.78) and moderate correlations between GSV cycle counts and cycling mode share (0.51). Beta regression models predicted mode shares with $R^2$ values of 0.614 for cycling and 0.612 for motorcycling, achieving median absolute errors (MDAE) of 1.3% and 1.4%, respectively. Scatterplots demonstrated consistent prediction accuracy, though cities like Utrecht and Cali were outliers. The model was applied to 60 cities globally for which we didn't have recent mode share data. We provided estimates for some cities in the Middle East, Latin America and East Asia. With computer vision, GSV images capture travel modes and activity, providing insights alongside traditional data sources.

cs.CV↗
arXiv2025

GraphRAG-Causal: A novel graph-augmented framework for causal reasoning and annotation in news

GraphRAG-Causal introduces an innovative framework that combines graph-based retrieval with large language models to enhance causal reasoning in news analysis. Traditional NLP approaches often struggle with identifying complex, implicit causal links, especially in low-data scenarios. Our approach addresses these challenges by transforming annotated news headlines into structured causal knowledge graphs. It then employs a hybrid retrieval system that merges semantic embeddings with graph-based structural cues leveraging Neo4j to accurately match and retrieve relevant events. The framework is built on a three-stage pipeline: First, during Data Preparation, news sentences are meticulously annotated and converted into causal graphs capturing cause, effect, and trigger relationships. Next, the Graph Retrieval stage stores these graphs along with their embeddings in a Neo4j database and utilizes hybrid Cypher queries to efficiently identify events that share both semantic and structural similarities with a given query. Finally, the LLM Inference stage utilizes these retrieved causal graphs in a few-shot learning setup with XML-based prompting, enabling robust classification and tagging of causal relationships. Experimental evaluations demonstrate that GraphRAG-Causal achieves an impressive F1-score of 82.1% on causal classification using just 20 few-shot examples. This approach significantly boosts accuracy and consistency, making it highly suitable for real-time applications in news reliability assessment, misinformation detection, and policy analysis.

cs.IR↗
arXiv2024

Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art.

cs.LG↗
arXiv2023

Urdu Poetry Generated by Using Deep Learning Techniques

This study provides Urdu poetry generated using different deep-learning techniques and algorithms. The data was collected through the Rekhta website, containing 1341 text files with several couplets. The data on poetry was not from any specific genre or poet. Instead, it was a collection of mixed Urdu poems and Ghazals. Different deep learning techniques, such as the model applied Long Short-term Memory Networks (LSTM) and Gated Recurrent Unit (GRU), have been used. Natural Language Processing (NLP) may be used in machine learning to understand, analyze, and generate a language humans may use and understand. Much work has been done on generating poetry for different languages using different techniques. The collection and use of data were also different for different researchers. The primary purpose of this project is to provide a model that generates Urdu poems by using data completely, not by sampling data. Also, this may generate poems in pure Urdu, not Roman Urdu, as in the base paper. The results have shown good accuracy in the poems generated by the model.

cs.CL↗
arXiv2019

Semigroup associated with a free polynomial

Let $\mathbb{K}$ be an algebraically closed field of characteristic zero and let $\mathbb{K}_{C}[[x_{1},...,x_{e}]]$ be the ring of formal power series in several variables with exponents in a line free cone $C$. We consider irreducible polynomials $f=y^n+a_1(\underline{x})y^{n-1}+\ldots+a_n(\underline{x})$ in $\mathbb{K}_{C}[[x_{1},...,x_{e}]][y]$ whose roots are in $\mathbb{K}_{C}[[x_{1}^{\frac{1}{n}},...,x_{e}^{\frac{1}{n}}]]$. We generalize to these polynomials the theory of Abhyankar-Moh. In particular we associate with any such polynomial its set of characteristic exponents and its semigroup of values. We also prove that the set of values can be obtained using the set of approximate roots. We finally prove that polynomials of ${\mathbb K}[[\underline{x}]][y]$ fit in the above set for a specific line free cone (see Section 4).

math.AG↗
arXiv2015

The Propensity to Cycle Tool: An open source online system for sustainable transport planning

Getting people cycling is an increasingly common objective in transport planning institutions worldwide. A growing evidence base indicates that high quality infrastructure can boost local cycling rates. Yet for infrastructure and other cycling measures to be effective, it is important to intervene in the right places, such as along 'desire lines' of high latent demand. This creates the need for tools and methods to help answer the question 'where to build?'. Following a brief review of the policy and research context related to this question, this paper describes the design, features and potential applications of such a tool. The Propensity to Cycle Tool (PCT) is an online, interactive planning support system which was initially developed to explore and map cycling potential across England (see www.pct.bike). Based on origin-destination data, it models and visualises cycling levels at area, desire line, route and route network levels, for current levels of cycling, and for scenario-based 'cycling futures'. Four scenarios are presented, including 'Go Dutch' and 'Ebikes', which explore what would happen if English people cycled as much as Dutch people and the potential impact of electric cycles on cycling uptake. The cost effectiveness of investment depends not only on the number of additional trips cycled, but on wider impacts such as health and carbon benefits. The PCT reports these at area, desire line, and route level for each scenario. The PCT is open source, facilitating the creation of additional scenarios and its deployment in new contexts. We conclude that the PCT illustrates the potential of online tools to inform transport decisions and raises the wider issue of how models should be used in transport planning.

cs.CY↗