Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i. e.
Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement. Standard single-objective models, including traditional Deep Q-Networks, are ill-equipped to navigate the trade-offs between platform retention and critical societal values like information diversity and provider fairness.
Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It also commonly relies on low degree-of-freedom (DoF) end effectors that behave like an open-close grasp primitive.
Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequential reasoning within a trace, independently sampled parallel traces, and aggregation of multiple reasoning traces into a final response. During post-training, however, language models are optimized only for sequential reasoning within a single trace.
In many online learning and bandit problems, the actions we consider possess inherent similarities--for instance because they share latent traits, tags, or hierarchical structure. We study online learning with a similarity-structured action set, encoded by a rooted tree whose leaves are the actions and whose levels quantify how closely two actions are related.
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train--deployment prompt mismatch.
Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $δ$-explicit minimax-quantile theory for interactive statistical decision making (ISDM).
Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at inference time. In this work, we theoretically analyze why reinforcement fine-tuning induces better reasoning ability than purely supervised fine-tuning (SFT) methods.
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages.
Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primarily rely on motion capture datasets, which are expensive to scale and limited in functional diversity.
Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Existing variance-reduction techniques typically rely on myopic magnitude checks, which fail to distinguish informative geometric signals from impulsive outliers.
Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sampling priors are highly efficacious for standard iterative generation, consistency distillation exhibits a distinctly different difficulty profile (e.
LLM agents in knowledge intensive question answering take retrieval and reasoning actions with incomplete knowledge about whether their current answer is uncertain, unsupported, or already complete. This produces two failure modes: committing to confident but unsupported answers, which hurts accuracy, and over-retrieving when the evidence in hand already suffices, resulting in wasted compute.
arXiv:2606. 20280v1 Announce Type: cross Abstract: Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR).
arXiv:2606. 19527v1 Announce Type: new Abstract: Can Large Language Models (LLMs) discern when their own outputs are misaligned with human ethics?
arXiv:2606. 20324v1 Announce Type: cross Abstract: Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior.
arXiv:2606. 19690v1 Announce Type: new Abstract: From the past few years, web intelligent enhancement systems increasingly rely on heterogeneous and dynamic web data to deliver personalized, context-aware services.
arXiv:2606. 20482v1 Announce Type: cross Abstract: To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text.
arXiv:2606. 20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment.
arXiv:2606. 20031v1 Announce Type: cross Abstract: Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS) a challenging problem for conventional search- and rule-based methods, which typically suffer from high computational complexity and long decision latency.