Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2601. 09285v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge.
arXiv:2606. 08147v1 Announce Type: cross Abstract: DNA cis-regulatory elements (CREs) such as enhancers control gene expression levels.
arXiv:2601. 21754v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel in language-based agentic tasks, their applicability to unseen, nonlinguistic environments (e.
arXiv:2606. 08875v1 Announce Type: new Abstract: Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance.
arXiv:2606. 09802v1 Announce Type: cross Abstract: We consider a variant of the linear contextual stochastic multi-armed bandits, where the learner must provide recommendations to a group of users, each having its personalized preference vector, and in the presence of context distributions that are drifting over time.
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
arXiv:2605. 17609v2 Announce Type: replace Abstract: Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation.
arXiv:2603. 03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.
arXiv:2606. 09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories.
arXiv:2509. 25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems.
arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.
arXiv:2606. 07610v1 Announce Type: cross Abstract: State-of-the-art GRPO-style methods for speech-aware large language model post-training suffer from coarse credit assignment, broadcasting the same terminal-reward advantage to every token in a response.
arXiv:2606. 08533v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are increasingly being deployed in logistics, service robotics, and other real-world applications, creating a growing demand for autonomous payload acquisition and delivery.
arXiv:2601. 01665v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has shown great promise in addressing multi-objective combinatorial optimization problems (MOCOPs).
arXiv:2601. 23286v4 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift.
arXiv:2606. 09821v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs).
arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.
arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.
arXiv:2606. 07550v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky.
arXiv:2606. 08379v1 Announce Type: new Abstract: This study addresses the optimal execution of large stock sell programs by introducing TT-DAC-PS (Twin-Target Deterministic Actor-Critic with Policy Smoothing), a deterministic actor-critic architecture that combines twin exponential-moving-average critic targets with pessimistic min backup, TD3-style target policy smoothing noise, delayed actor updates, and conservative Q regularisation to curb overestimation.