Related papers: CoVerRL: Breaking the Consensus Trap in Label-Free…
Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth verifiable rewards, restricting training to domains with automatic correctness checks…
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…
Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans) or limited in utility (e.g., tools like Lean). While LM…
Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free…
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration,…
Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent…
The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…
Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…
Large Language Models (LLMs) often rely on test-time scaling via parallel decoding (for example, 512 samples) to boost reasoning accuracy, but this incurs substantial compute. We introduce CoRefine, a confidence-guided self-refinement…
Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs.…
Reinforcement Learning from Verifiable Rewards (RLVR) suffers from exploration inefficiency, where models struggle to generate successful rollouts, resulting in minimal learning signal. This challenge is particularly severe for tasks that…
Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…
Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…
Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a…
Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…
Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…
In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However, existing self-evolution methods predominantly rely on…
Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled…
In this work, we address the real-world, challenging task of out-of-context misinformation detection, where a real image is paired with an incorrect caption for creating fake news. Existing approaches for this task assume the availability…