Related papers: SPLADE-v3: New baselines for SPLADE

Recent advances in large language models (LLMs) have opened new opportunities for academic literature retrieval. However, existing systems often rely on rigid pipelines and exhibit limited reasoning capabilities. We introduce SPAR, a…

Dealing with tabular data is challenging due to partial information, noise, and heterogeneous structure. Existing techniques often struggle to simultaneously address key aspects of tabular data such as textual information, a variable number…

Self-Supervised Learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be…

Recent foundation models are capable of handling multiple tasks and multiple data modalities with the unified base model structure and several specialized model components. However, efficient training of such multi-task (MT) multi-modal…

Benchmarks like SWE-bench have standardized the evaluation of Large Language Models (LLMs) on repository-level software engineering tasks. However, these efforts remain limited by manual curation, static datasets, and a focus on…

Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical question: can LLM-based…

Model-based meta-reinforcement learning (RL) methods have recently been shown to be a promising approach to improving the sample efficiency of RL in multi-task settings. However, the theoretical understanding of those methods is yet to be…

Training large language models (LLMs) for reasoning via maths and code datasets has become a major new focus in LLM post-training. Two particularly popular approaches are reinforcement learning (RL) and supervised fine-tuning (SFT), but…

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for…

Offline multi-agent reinforcement learning (MARL) is an emerging field with great promise for real-world applications. Unfortunately, the current state of research in offline MARL is plagued by inconsistencies in baselines and evaluation…

Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…

Multi-Agent Reinforcement Learning (MARL) has enjoyed significant recent progress thanks, in part, to the integration of deep learning techniques for modeling interactions in complex environments. This is naturally starting to benefit…

In the era of Big Data and the growing support for Machine Learning, Deep Learning and Artificial Intelligence algorithms in the current software systems, there is an urgent need of standardized application benchmarks that stress test and…

Learned Sparse Retrieval (LSR) models encode text as weighted term vectors, which need to be sparse to leverage inverted index structures during retrieval. SPLADE, the most popular LSR model, uses FLOPS regularization to encourage vector…

This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing…

Resource scheduling in cloud-edge systems is challenging as edge nodes run latency-sensitive workloads under tight resource constraints, while existing centralized schedulers can suffer from performance bottlenecks and user experience…

Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM…

Pre-trained language models (PLMs) have achieved outstanding achievements in abstractive single-document summarization (SDS). However, such benefits may not fully extend to multi-document summarization (MDS), where the handling of…

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…