Related papers: TR-ICRL: Test-Time Rethinking for In-Context Reinf…
Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…
In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent on the selection of these demonstrations. Recent work…
The successes of reinforcement learning in recent years are underpinned by the characterization of suitable reward functions. However, in settings where such rewards are non-intuitive, difficult to define, or otherwise error-prone in their…
Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…
While Large Language Models (LLMs) have exhibited remarkable emergent capabilities through extensive pre-training, they still face critical limitations in generalizing to specialized domains and handling diverse linguistic variations, known…
We introduce SAIL-RL, a reinforcement learning (RL) post-training framework that enhances the reasoning capabilities of multimodal large language models (MLLMs) by teaching them when and how to think. Existing approaches are limited by…
Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…
In-context learning with large language models (LLMs) excels at adapting to various tasks rapidly. However, its success hinges on carefully selecting demonstrations, which remains an obstacle in practice. Current approaches to this problem…
Large language models (LLMs) exhibit impressive in-context learning (ICL) capabilities, yet the quality of their predictions is fundamentally limited by the few costly labeled demonstrations that can fit into a prompt. Meanwhile, there…
Large Language Models (LLM) hold immense promise for real-world applications, but their generic knowledge often falls short of domain-specific needs. Fine-tuning, a common approach, can suffer from catastrophic forgetting and hinder…
Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language. Combined with in-context learning (ICL), this…
Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…
The rapid progress of large language models (LLMs) has led to remarkable performance gains across a wide range of tasks. However, when handling long documents that exceed the model's context window limit, the entire context cannot be…
Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with…
Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…
The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach…
Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…
In-Context Learning (ICL) has emerged as an important new paradigm in natural language processing and large language model (LLM) applications. However, the theoretical understanding of the ICL mechanism remains limited. This paper aims to…
Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts,…
Urban congestion remains a critical challenge, with traffic signal control (TSC) emerging as a potent solution. TSC is often modeled as a Markov Decision Process problem and then solved using reinforcement learning (RL), which has proven…