Related papers: Learning Randomized Reductions
The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…
Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various…
Reinforcement learning (RL) is concerned with how intelligence agents take actions in a given environment to maximize the cumulative reward they receive. In healthcare, applying RL algorithms could assist patients in improving their health…
Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying…
Automatically detecting and recovering from failures is an important but challenging problem for autonomous robots. Most of the recent work on learning to plan from demonstrations lacks the ability to detect and recover from errors in the…
Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to…
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…
Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models, but rewards only final-answer correctness with no supervision over intermediate steps. Rubric-based methods such as Rubrics…
Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative…
Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…
Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). However, extending this paradigm to open-ended generation is…
Visual pointing, which aims to localize a target by predicting its coordinates on an image, has emerged as an important problem in the realm of vision-language models (VLMs). Despite its broad applicability, recent benchmarks show that…
Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…
When an RL agent's observations contain distractors driven by the same confounders as its true state, observational data alone cannot identify which dimensions the agent controls. In our benchmarks, even state-conditioned observational…
We tackle the challenge of training reliable code-fixing agents in real repositories, where complex builds and shifting dependencies make evaluation unstable. We developed a verifiable pipeline with success defined as post-fix build…
Deep learning has significantly advanced medical imaging analysis, yet variations in image resolution remain an overlooked challenge. Most methods address this by resampling images, leading to either information loss or computational…
Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine…
Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular…
Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a…