This position paper argues that the text embedding research community should move beyond surface meaning and embrace implicit semantics as a central modeling goal. Text embedding models have become foundational in modern NLP, powering a wide range of applications and drawing increasing research attention. Yet, much of this progress remains narrowly focused on surface-level semantics. In contrast, linguistic theory emphasizes that meaning is often implicit, shaped by pragmatics, speaker intent, and sociocultural context. Current embedding models are typically trained on data that lacks such depth and evaluated on benchmarks that reward the capture of surface meaning. As a result, they struggle with tasks requiring interpretive reasoning, speaker stance, or social meaning. Our pilot study highlights this gap, showing that even state-of-the-art models perform only marginally better than simplistic baselines on implicit semantics tasks. To address this, we call for a paradigm shift: embedding research should prioritize more diverse and linguistically grounded training data, design benchmarks that evaluate deeper semantic understanding, and explicitly frame implicit meaning as a core modeling objective, better aligning embeddings with real-world language complexity.

Task vectors offer a compelling mechanism for accelerating inference in in-context learning (ICL) by distilling task-specific information into a single, reusable representation. Despite their empirical success, the underlying principles governing their emergence and functionality remain unclear. This work proposes the Linear Combination Conjecture, positing that task vectors act as single in-context demonstrations formed through linear combinations of the original ones. We provide both theoretical and empirical support for this conjecture. First, we show that task vectors naturally emerge in linear transformers trained on triplet-formatted prompts through loss landscape analysis. Next, we predict the failure of task vectors on representing high-rank mappings and confirm this on practical LLMs. Our findings are further validated through saliency analyses and parameter visualization, suggesting an enhancement of task vectors by injecting multiple ones into few-shot prompts. Together, our results advance the understanding of task vectors and shed light on the mechanisms underlying ICL in transformer-based models.

For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecified, ill-posed, or fundamentally unanswerable, require LLMs to reason about uncertainty and selectively abstain -- i.e., refuse to answer definitively. However, abstention remains understudied, without a systematic evaluation framework for modern LLMs. In this work, we introduce AbstentionBench, a large-scale benchmark for holistically evaluating abstention across 20 diverse datasets, including questions with unknown answers, underspecification, false premises, subjective interpretations, and outdated information. Evaluating 20 frontier LLMs reveals abstention is an unsolved problem, and one where scaling models is of little use. While recent reasoning LLMs have shown impressive results in complex problem solving, surprisingly, we find that reasoning fine-tuning degrades abstention (by $24\%$ on average), even for math and science domains on which reasoning models are explicitly trained. We find that while a carefully crafted system prompt can boost abstention in practice, it does not resolve models' fundamental inability to reason about uncertainty. We release AbstentionBench to foster research into advancing LLM reliability.

-- Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contrastive learning (CLIP-based) methods suffer from suboptimal visual representation capabilities, which also limits their effectiveness in vision-language alignment. In contrast, although the models pretrained via multimodal masked modeling struggle with direct cross-modal matching, they excel in visual representation. To address this contradiction, we propose ALTA (ALign Through Adapting), an efficient medical vision-language alignment method that utilizes only about 8% of the trainable parameters and less than 1/5 of the computational consumption required for masked record modeling. ALTA achieves superior performance in vision-language matching tasks like retrieval and zero-shot classification by adapting the pretrained vision model from masked record modeling. Additionally, we integrate temporal-multiview radiograph inputs to enhance the information consistency between radiographs and their corresponding descriptions in reports, further improving the vision-language alignment. Experimental evaluations show that ALTA outperforms the best-performing counterpart by over 4% absolute points in text-to-image accuracy and approximately 6% absolute points in image-to-text re-This work was supported by National Natural Science Foundation of China (Grant No. 62371409), Fujian Provincial Natural Science Foundation of China (Grant No. 2023J01005), Innovation and T ech-nology Fund under Hong Kong Innovation and T echnology Commission (Project No. ITS/202/23), Collaborative Research with World-leading Research Groups in The Hong Kong Polytechnic University (Project No. G-SACF), and a Shenzhen-Hong Kong-Macao Science and T echnology Plan Project (Category C Project) under Shenzhen Municipal Science and T echnology Innovation Commission (project no SGDX20230821092359002). Hong-Y u Zhou is with the Department of Biomedical Informatics, Harvard Medical School, Boston, USA (e-mail: whuzhouhongyu@gmail.com). Dongyun Liang is with the Department of Radiology, Zhongshan Hospital (Xiamen), Fudan University, Xiamen Municipal Clinical Research Center for Medical Imaging, Fujian Province Key Clinical Specialty for Medical Imaging, Xiamen Key Laboratory of Clinical T ransformation of Imaging Big Data and Artificial Intelligence, Xiamen 361015, China (email: ldy7372@163.com). Liansheng Wang is with the National Institute for Data Science in Health and Medicine, and the Department of Computer Science, School of Informatics, Xiamen University, Xiamen 361005, China (email: lswang@xmu.edu.cn). Jing Qin is with the Center for Smart Health, School of Nursing, The Hong Kong Polytechnic University, Hong Kong, China (e-mail: harry .qin@polyu.edu.hk).

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for training large language models (LLMs) on complex reasoning tasks, such as mathematical problem solving. A prerequisite for the scalability of RLVR is a high-quality problem set with precise and verifiable answers. However, the scarcity of well-crafted human-labeled math problems and limited-verification answers in existing distillation-oriented synthetic datasets limit their effectiveness in RL. Additionally, most problem synthesis strategies indiscriminately expand the problem set without considering the model's capabilities, leading to low efficiency in generating useful questions. To mitigate this issue, we introduce a Self-aware Weakness-driven problem Synthesis framework (SwS) that systematically identifies model deficiencies and leverages them for problem augmentation. Specifically, we define weaknesses as questions that the model consistently fails to learn through its iterative sampling during RL training. We then extract the core concepts from these failure cases and synthesize new problems to strengthen the model's weak areas in subsequent augmented training, enabling it to focus on and gradually overcome its weaknesses. Without relying on external knowledge distillation, our framework enables robust generalization byempowering the model to self-identify and address its weaknesses in RL, yielding average performance gains of 10.0% and 7.7% on 7B and 32B models across eight mainstream reasoning benchmarks.

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that enables generative reward models trained on small datasets to achieve comparable performance to those trained on large-scale datasets. Traditional methods to train a generative reward model, such as Direct Preference Optimization (DPO), are constrained by inefficiencies in sample pairing and limited data diversity. This work introduces preference refinement, which employs Chain-of-Thought (CoT) sampling to uncover diverse and high-quality preference relationships. It also incorporates a perplexity-based scoring mechanism to assign nuanced preference levels and utilizes Multi-level Direct Preference Optimization (M-DPO) to enable the model to capture finer-grained preference differences between samples. Experimental results demonstrate that the proposed method significantly enhances data efficiency and model performance, enabling reward models trained in a few-shot setting to achieve results on par with those trained on large-scale datasets. This study underscores the potential of data-efficient strategies in advancing reward model optimization, offering a robust solution for low-resource RLHF applications.

This research-to-practice work-in-progress (WIP) paper presents an AI-enabled smart tutor designed to provide homework assessment and feedback for students in an undergraduate circuit analysis course. We detail the tutor's design philosophy and core components, including open-ended question answering and homework feedback generation. The prompts are carefully crafted to optimize responses across different problems. The smart tutor was deployed on the Microsoft Azure platform and is currently in use in an undergraduate circuit analysis course at the School of Electrical and Computer Engineering in a large, public, research-intensive institution in the Southeastern United States. Beyond offering personalized instruction and feedback, the tutor collects student interaction data, which is summarized and shared with the course instructor. To evaluate its effectiveness, we collected student feedback, with 90.9% of responses indicating satisfaction with the tutor. Additionally, we analyze a subset of collected data on preliminary circuit analysis topics to assess tutor usage frequency for each problem and identify frequently asked questions. These insights help instructors gain real-time awareness of student difficulties, enabling more targeted classroom instruction. In future work, we will release a full analysis once the complete dataset is available after the Spring 2025 semester. We also explore the potential applications of this smart tutor across a broader range of engineering disciplines by developing improved prompts, diagram-recognition methods, and database management strategies, which remain ongoing areas of research.

Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows have relied on a two-step process: first retrieving homologs via Multiple Sequence Alignments (MSA), then training models on one or more of these alignments. However, MSA-based retrieval is computationally expensive, struggles with highly divergent sequences or complex insertions & deletions patterns, and operates independently of the downstream modeling objective. We introduce Protriever, an end-to-end differentiable framework that learns to retrieve relevant homologs while simultaneously training for the target task. When applied to protein fitness prediction, Protriever achieves state-of-the-art performance compared to sequence-based models that rely on MSA-based homolog retrieval, while being two orders of magnitude faster through efficient vector search. Protriever is both architecture- and task-agnostic, and can flexibly adapt to different retrieval strategies and protein databases at inference time -- offering a scalable alternative to alignment-centric approaches.

We present BioLangFusion, a simple approach for integrating pre-trained DNA, mRNA, and protein language models into unified molecular representations. Motivated by the central dogma of molecular biology (information flow from gene to transcript to protein), we align per-modality embeddings at the biologically meaningful codon level (three nucleotides encoding one amino acid) to ensure direct cross-modal correspondence. BioLangFusion studies three standard fusion techniques: (i) codon-level embedding concatenation, (ii) entropy-regularized attention pooling inspired by multiple-instance learning, and (iii) cross-modal multi-head attention -- each technique providing a different inductive bias for combining modality-specific signals. These methods require no additional pre-training or modification of the base models, allowing straightforward integration with existing sequence-based foundation models. Across five molecular property prediction tasks, BioLangFusion outperforms strong unimodal baselines, showing that even simple fusion of pre-trained models can capture complementary multi-omic information with minimal overhead.

While large language models (LLMs) have achieved remarkable performance in various tasks including mathematical reasoning, their development typically demands prohibitive computational resources. Recent advancements have reduced costs for training capable models, yet even these approaches rely on high-end hardware clusters. In this paper, we demonstrate that a single average gaming GPU can train a solid mathematical reasoning model, by integrating reinforcement learning and memory optimization techniques. Specifically, we train a 1.5B parameter mathematical reasoning model on RTX 3080 Ti of 16GB memory that achieves comparable or better performance on mathematical reasoning benchmarks than models several times larger, in resource-constrained environments. Our results challenge the paradigm that state-of-the-art mathematical reasoning necessitates massive infrastructure, democratizing access to high-performance AI research. https://github.com/shinandrew/YouronMath.