Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal perception of when events occur. Existing MLLMs usually generate captions directly from video inputs without exposing the perceptual evidence behind descriptions.
In this report, we present a unified song generation framework capable of producing high-quality full-length music from lyrics, text descriptions, and musical attributes. The proposed framework supports three tasks: Lyrics-to-Song Generation, which generates complete songs from text descriptions, lyrics, and musical attributes; Instrumental Music Generation, which creates music without vocals; and Cover Song Generation, which reinterprets existing songs with different styles while preserving their melodic content.
The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints, and a scarcity of labeled data. Although the question of OLED generation is important, few models have been trained effectively for this specific domain.
Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e. g.
Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards valid evidence, whereas uncritical adoption yields incorrect or unsafe answers.
Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level.
In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations. The value and action-value (Q-value) functions are treated as uncertain quantities, and their estimation is formulated as a stochastic inference problem.
Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon agent safety that trains guards to anticipate delayed risks from partial trajectories.
arXiv:2607. 18589v1 Announce Type: cross Abstract: Reinforcement learning is conventionally divided into model-based and model-free methods.
arXiv:2508. 14751v2 Announce Type: replace Abstract: We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces.
arXiv:2607. 19345v1 Announce Type: cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier.
arXiv:2509. 08654v2 Announce Type: replace-cross Abstract: Quantum network routing requires online decisions under probabilistic entanglement generation, finite quantum memories, decoherence, imperfect operations, and classical feedback, while the controller has incomplete knowledge of the physical state.
arXiv:2606. 04484v2 Announce Type: replace Abstract: Training reinforcement learning (RL) policies for large language model (LLM) agents requires optimizing multi-turn trajectories that interact with external environments.
arXiv:2607. 18874v1 Announce Type: new Abstract: Using Unmanned Aerial Vehicle (UAV) for urban sensing has emerged as a powerful paradigm to monitor the status of the city, e.
arXiv:2607. 18722v1 Announce Type: new Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing.
arXiv:2607. 18830v1 Announce Type: cross Abstract: Model-Agnostic Meta-Learning (MAML) is a widely used framework for reinforcement learning (RL) that enables efficient transfer by learning global policy parameters that can be rapidly adapted to new tasks.
arXiv:2607. 19226v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has been established as a viable paradigm for the post-training of Large Language Models (LLMs), including downstream tasks, such as Neural Machine Translation (NMT).
arXiv:2607. 19232v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution.
arXiv:2607. 18597v1 Announce Type: new Abstract: Counterfactual credit assignment has proven effective in multi-agent reinforcement learning (MARL) for discrete action spaces, yet its extension to continuous-action cooperative tasks remains challenging.
arXiv:2607. 18488v1 Announce Type: cross Abstract: Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations.