Related papers: PEER: Unified Process-Outcome Reinforcement Learni…
Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation. This explanation highlights how available information in a specific query is utilised and supplemented with information a reasoner…
Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…
Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to…
Empathetic response generation, aiming to understand the user's situation and feelings and respond empathically, is crucial in building human-like dialogue systems. Traditional approaches typically employ maximum likelihood estimation as…
Group Relative Policy Optimization (GRPO), which is widely adopted by R1-like reasoning models, has advanced mathematical reasoning. Nevertheless, GRPO faces challenges in reward sparsity, verbosity, and inadequate focus on problem…
Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that…
The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size-fits-all' approach for predicting emotion. Moreover,…
Speech emotion recognition (SER) has long benefited from the adoption of deep learning methodologies. Deeper models -- with more layers and more trainable parameters -- are generally perceived as being `better' by the SER community. This…
We are now witnessing significant progress of deep learning methods in a variety of tasks (or datasets) of proteins. However, there is a lack of a standard benchmark to evaluate the performance of different methods, which hinders the…
Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improve, creating a self-loop system of training. However, existing works are limited in…
Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models. Yet existing methods share a common blind spot: they optimize policies…
In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to…
Multimodal emotion recognition in conversations (MERC) requires integrating multimodal signals while being robust to noise and modeling contextual reasoning. Existing approaches often emphasize fusion but overlook uncertainty in noisy…
Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…
The development of models of human sentence processing has traditionally followed one of two paths. Either the model posited a sequence of processing modules, each with its own task-specific knowledge (e.g., syntax and semantics), or it…
Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the…
A significant hurdle for current LLMs is the execution of complex, multi-stage tasks. Group Relative Policy Optimization (GRPO) has been emerging as a leading choice, but its reliance on sparse outcome rewards severely limits credit…
Recent approaches for empathetic response generation mainly focus on emotional resonance and user understanding, without considering the system's personality. Consistent personality is evident in real human expression and is important for…
Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…
Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by label spaces, enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative…