相关论文: AMARIS: A Memory-Augmented Rubric Improvement Syst…

Large Reasoning Language Models (LRLMs or LRMs) demonstrate remarkable capabilities in complex reasoning tasks, but suffer from significant computational inefficiencies due to overthinking phenomena. Existing efficient reasoning methods…

Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs…

Aligning Text-to-Image (T2I) generation models with human preferences increasingly relies on image reward models that score or rank generated images according to prompt alignment and perceptual quality. Existing reward models are commonly…

This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG (R2RAG), a research-focused retrieval-augmented generation (RAG) architecture composed…

We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal: instead of a binary outcome or a single holistic score, each response is graded along…

One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are…

The integration of large language models (LLMs) into medical practice offers transformative potential, yet their real-world clinical applicability remains constrained by critical alignment issues: (1) a misalignment between static…

Student responses in STEM assessments are often handwritten and combine symbolic expressions, calculations, and diagrams, creating substantial variation in format and interpretation. Despite their importance for evaluating students'…

Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and the long reasoning horizon make effective exploration challenging. In practice, this…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Class-Incremental Learning (CIL) [40] trains classifiers under a strict memory budget: in each incremental phase, learning is done for new data, most of which is abandoned to free space for the next phase. The preserved data are exemplars…

Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience.…

With the rapid advancement of large language models (LLMs), reinforcement learning (RL) has emerged as a pivotal methodology for enhancing the reasoning capabilities of LLMs. Unlike traditional pre-training approaches, RL encompasses…

AI-driven Action Quality Assessment (AQA) of sports videos can mimic Olympic judges to help score performances as a second opinion or for training. However, these AI methods are uninterpretable and do not justify their scores, which is…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Hallucination remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While Direct Preference Optimization (DPO) is a key alignment framework, existing approaches often rely heavily on costly external evaluators for…

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies…

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…