Related papers: Contrastive Reasoning Alignment: Reinforcement Lea…

In this paper, we introduce a method for unifying language, action, and state information in a shared embedding space to facilitate a range of downstream tasks in robot learning. Our method, Contrastive Language, Action, and State…

Despite the impressive feats demonstrated by Reinforcement Learning (RL), these algorithms have seen little adoption in high-risk, real-world applications due to current difficulties in explaining RL agent actions and building user trust.…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow learning from contextual information. Humans use context to…

Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…

Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…

Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This…

Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment. As a primary countermeasure, adversarial training improves…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

For a long time the ability to solve abstract reasoning tasks was considered one of the hallmarks of human intelligence. Recent advances in application of deep learning (DL) methods led, as in many other domains, to surpassing human…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

The deep neural networks (DNNs) have freed the synthetic aperture radar automatic target recognition (SAR ATR) from expertise-based feature designing and demonstrated superiority over conventional solutions. There has been shown the unique…

Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs…

Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation, where models generate segmentation masks based on textual queries. While prior work has primarily focused…

Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible…

Reinforcement Learning (RL) has played a central role in the recent surge of LLMs' math abilities by enabling self-improvement through binary verifier signals. In contrast, Supervised Learning (SL) is rarely considered for such…

Contrastive learning is a significant paradigm in graph self-supervised learning. However, it requires negative samples to prevent model collapse and learn discriminative representations. These negative samples inevitably lead to heavy…

Language Reasoning Models (LRMs) achieve strong performance by scaling test-time computation but often suffer from ``overthinking'', producing excessively long reasoning traces that increase latency and memory usage. Existing LRMs typically…

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

We propose the Uncertainty Contrastive Framework (UCF), a Positive-Unlabeled (PU) representation learning framework that integrates uncertainty-aware contrastive loss, adaptive temperature scaling, and a self-attention-guided LSTM encoder…