Papers with a repository link where Syntology ran at least one harvested code sample. Each page shows two streams, newest first within each, counted separately: papers newer than the archive snapshot come from Syntology's graph Syntology; the rest are archive rows archive 2025-07-28. The two are never added together.
Cards 61–75 of 5,105 graph papers newer than 2025-07-28 with a Syntology-ran sample; this feed shows the newest 150, newest arXiv id first. Dates and the abstract sentence are from arXiv's metadata (CC0) for 5,105 of 5,105.
Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective.
Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently faces a critical dilemma: researchers must choose between sparse…
Data-driven prognostics and health management has emerged as a key enabler for Industry 4.0, yet the development of robust remaining useful life (RUL) estimation models is often limited by the scarcity of run-to-failure…
Parameter-Efficient Fine-Tuning (PEFT) strategies such as Low-Rank Adaptation (LoRA) are effective solutions for fine-tuning large-scale pre-trained models; however, their memory requirements scale with the size of the…
SVD-based low-rank compression has become a fast-growing direction for reducing the memory and computational cost of large language models (LLMs).
Volume-based accuracy rewards retrieval-augmented generation (RAG) systems for guessing: a system that answers everything outscores one that declines when its knowledge base cannot support an answer.
Whether large language models (LLMs) can perform the abductive leap from evidence to a new system of axioms, commonly referred to as a jump, has recently attracted considerable debate.
Referring Expression Segmentation (RES) aims to generate pixel-wise segmentation masks from complex and implicit textual queries.
Whether large language models can be prompted to generate rhetorical fallacies on demand, and whether current safety post-training constrains this behavior, has received less attention than the related question of…
Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe are all specified by hand.
Understanding instruction-following capabilities in scientific domains is essential for effectively leveraging Multimodal Large Language Models (MLLMs) to advance the development of scientific fields.
Control variables are widely used in statistical modelling to account for omitted variable bias of known confounders.
We address the simultaneous prediction of multiple high-dimensional physical fields governed by linear equality constraints, a setting that arises in many real-world applications in physics machine learning.
Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging memory systems.
The purpose of this paper is to provide a general, comprehensive, theoretical framework that allows one to deal with fibrations on graphs labelled on a commutative monoid.
Cards 61–75 of 31,700 archive papers with a code link, filtered to those where Syntology ran at least one sample (the archive chip labels the rows, the Syntology chip labels the filter; the count is the archive rows that pass it); this feed shows the newest 150, archive date first (newest archive date 2025-07-17). Within a month, dated rows come first, then the 819 undated rows placed by the month in their arXiv id. 1 archive paper with neither a date nor an arXiv id cannot be placed and is not listed.
Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence.
Traditional wind farm control operates each turbine independently to maximize individual power output.
With the rapid advancement of deep learning, particularly through generative adversarial networks (GANs) and diffusion models (DMs), AI-generated images, or ``deepfakes", have become nearly indistinguishable from real…
Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive tasks.
Quantized large language models (LLMs) have gained increasing attention and significance for enabling deployment in resource-constrained environments.
Wildfires are increasing in intensity and severity at an alarming rate.
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings.
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge.
Large language models (LLMs) predominantly use autoregressive (AR) approaches, but masked diffusion models (MDMs) are emerging as viable alternatives.
To understand how genetic variants in human genomes manifest in phenotypes -- traits like height or diseases like asthma -- geneticists have sequenced and measured hundreds of thousands of individuals.
Reasoning large language models have recently achieved state-of-the-art performance in many fields.
Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows.
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation.
Ultra-long generation by large language models (LLMs) is a widely demanded scenario, yet it remains a significant challenge due to their maximum generation length limit and overall quality degradation as sequence length…
Continuous chain-of-thought has been shown to be effective in saving reasoning tokens for large language models.
The feed is static: 10 pages of up to 15 cards per stream, rebuilt with the site. Older papers are reachable from task, dataset and method pages and from search. No repository stars are tracked and nothing here is ranked by popularity. Machine-readable twin: JSON.