Related papers: SAGE: Sequence-level Adaptive Gradient Evolution f…

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete…

Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical…

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse…

Large language model (LLM) based recommendation agents personalize what they know through evolving per-user semantic memory, yet how they reason remains a universal, static system prompt shared identically across all users. This asymmetry…

While deep learning approaches have shown remarkable performance in many imaging tasks, most of these methods rely on availability of large quantities of data. Medical image data, however, is scarce and fragmented. Generative Adversarial…

As large language models (LLMs) achieve strong performance on traditional benchmarks, there is an urgent need for more challenging evaluation frameworks that probe deeper aspects of semantic understanding. We introduce SAGE (Semantic…

The vision of an inclusive World Wide Web is impeded by a severe linguistic divide, particularly for communities in low-resource regions of Southeast Asia. While large language models (LLMs) offer a potential solution for translation, their…

Training modern neural networks on large datasets is computationally and energy intensive. We present SAGE, a streaming data-subset selection method that maintains a compact Frequent Directions (FD) sketch of gradient geometry in $O(\ell…

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…

Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets.…

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture…

Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Although Large Language Models (LLMs) offer rich semantic priors…

Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. If domain invariant representations have dramatically…

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image…

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be…

Sequential recommender systems have demonstrated strong capabilities in modeling users' dynamic preferences and capturing item transition patterns. However, real-world user behaviors are often noisy due to factors such as human errors,…

Music streaming fraud, where bad actors artificially inflate stream counts to manipulate chart rankings and royalty payments, poses a significant threat to streaming services and legitimate content creators. Traditional fraud detection…

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…