Related papers: EvoSyn: Generalizable Evolutionary Data Synthesis …
Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution. We argue that striving for the…
Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty…
Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models such as DeepSeek-R1. In complex domains like mathematical…
Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…
Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches rely on sparse outcome-level feedback. This sparsity creates a credit assignment…
High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated by these generative…
Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than humans regarding…
Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current…
Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While…
Variable selection for high-dimensional, highly correlated data has long been a challenging problem, often yielding unstable and unreliable models. We propose a resample-aggregate framework that exploits diffusion models' ability to…
Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers,…
Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in…
Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…
Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…
While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge. Dataset distillation addresses these challenges by synthesizing…
Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…
Training language models to solve complex mathematical problems benefits from curriculum learning progressively training on simpler subproblems. However, existing decomposition methods are often heuristic, offering no guarantees that…
Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked by limited existing verifiable data, where improvements…
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is…
In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is…