RNA’s conformational flexibility enables diverse biological functions but makes structure-guided design difficult. Although precise control of 3D structure is essential, existing methods often overlook the molecular surface, which critically shapes intermolecular interactions and functional outcomes. To address this, we propose gRFold, a multimodal framework that incorporates molecular surface information as a core design constraint. gRFold employs two geometric encoders: a Frame-Averaged Geometric Surface Encoder (FA-GSE) to learn E(3)-invariant surface features, and an Equivariant Backbone Graph Perceptron (EBGP) to capture backbone topology. The structural representations are integrated via hierarchical cross-attention to guide autoregressive generation; at inference, candidates are re-ranked by agreement between their predicted folds and the target base-pairing pattern. Across three RNA inverse-folding benchmarks covering RNA-protein complexes, monomeric RNAs and independently curated RNA-Puzzles targets, gRFold achieves strong sequence recovery and structural fidelity under both secondary-structure and 3D refolding evaluations, and ablations show that the surface and backbone branches contribute complementary gains. These results highlight the potential of surface-aware geometric modeling for structure-guided RNA design.

Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output schema for a series of questions. On benchmarks that grade against every detail of the context, even strong open-weights models pass only 12-16% of tasks: a single overlooked rule fails the whole response. We argue this brittleness is structural—the dominant "read-and-reason" paradigm asks the model to extract, plan, generate, and self-verify in one forward pass—and ask whether explicit context compilation can fix it, how it compares to existing long-context strategies (gist retrieval, multi-agent self-play), and where the resulting harness benefit holds across task structure and model scale. We propose the Context Compilation Architecture (CCA): compile the given context into a structured IR of rules, schemas, and exact terms; generate executable verifiers from the IR; run a checked reasoning loop that corrects any violation those verifiers flag. On CL-bench (1,899 tasks across 4 open base models), CCA outperforms vanilla prompting and two long-context baselines (ReadAgent-P, Ctx2Skill) on every base model, lifting Kimi K2.5 from 15.4% to 21.4% with gains concentrated on rule-dense sub-categories.

Real-world data analysis often requires joint reasoning over heterogeneous artifacts such as tables, charts, and textual reports. Training reliable multimodal large language model (MLLM) agents for this setting remains challenging, as large-scale aligned training data are scarce, and outcome-only rewards are too coarse to distinguish grounded cross-source analysis from spurious success. We introduce OmniDA, a training recipe that addresses these two challenges with a scalable multimodal data-synthesis pipeline and an Evidence-Aware Process Reward (EAPR) that supervises both evidence recovery and procedural validity. Through this pipeline, we construct OmniDA-11K, a high-quality training corpus for multimodal data analysis. When instantiated with Qwen3-VL-8B, OmniDA improves over the corresponding agentic baseline by 19.2 points on average across five challenging benchmarks and achieves the strongest overall performance among existing open-source data-analysis agents. These results highlight the value of supervising evidence recovery and analytical procedure beyond final-answer correctness.

Text embeddings incorporate additional rich semantic information; however, their performance in sequential recommendation still falls short of that of ID embeddings. Decomposing item embeddings along the spectrum of the collaborative item–item graph reveals a distinct discrepancy in their spectral energy distribution. Task-learned ID embeddings concentrate their energy heavily in the low- and mid-frequency directions of the collaborative graph topology, while textual representations spread more uniformly across the entire spectrum. Motivated by this insight, we propose CASG, a learnable polynomial graph filter that shifts text embeddings toward ID embeddings via collaboration-aware spectral guidance. Specifically, it leverages collaborative relationships to actively guide and filter the spectral energy distribution of frozen text embeddings, selectively preserving the frequency components aligned with the collaborative topology in a single offline pass. Across three datasets and two text encoders, CASG consistently surpasses learned ID embeddings, alignment-based, and fusion-based baselines at no online cost, suggesting that what semantic representations need is neither more alignment nor more fusion but collaboration-aware spectral guidance. Our source code is available at https://github.com/blueColdSea/CASG.

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage–query relevance using the attention scores of selected heads. This approach provides a listwise solution that leverages the holistic information within the entire candidate shortlist during ranking. At the same time, it naturally produces continuous relevance scores, enabling training on arbitrary retrieval datasets without requiring Likert-scale supervision. Our framework is lightweight and effective, requiring only small-scale models (e.g., 4B parameters) to achieve strong performance. Extensive experiments demonstrate that our method outperforms existing state-of-the-art pointwise and listwise rerankers across multiple domains, including Wikipedia and long narrative datasets. It further establishes a new state-of-the-art on the LoCoMo benchmark that assesses the capabilities of dialogue understanding and memory usage. We further demonstrate that our framework supports flexible extensions. For example, augmenting candidate passages with contextual information further improves ranking accuracy, while training attention heads from middle layers enhances efficiency without sacrificing performance.

High-quality data resources play a crucial role in learning large language models (LLMs), particularly for low-resource languages like Cantonese. Despite having more than 85 million native speakers, Cantonese is still considered a low-resource language in the field of natural language processing (NLP) due to factors such as the dominance of Mandarin, lack of cohesion within the Cantonese-speaking community, diversity in character encoding and input methods, and the tendency of overseas Cantonese speakers to prefer using English. In addition, rich colloquial vocabulary of Cantonese, English loanwords, and code-switching characteristics add to the complexity of corpus collection and processing. To address these challenges, we collect Cantonese texts from a variety of sources, including open source corpora, Hong Kong-specific forums, Wikipedia, and Common Crawl data. We conduct rigorous data processing through language filtering, quality filtering, content filtering, and de-duplication steps, successfully constructing a high-quality Cantonese corpus of over 2 billion tokens for training large language models. We further refined the model through supervised fine-tuning (SFT) on curated Cantonese tasks, enhancing its ability to handle specific applications. Upon completion of the training, the model achieves state-of-the-art (SOTA) performance on four Cantonese benchmarks. After training on our dataset, the model also exhibits improved performance on other mainstream language tasks.