Biomedical Foundation Models (FMs) are rapidly transforming AI-enabled healthcare research and entering clinical validation. However, their susceptibility to learning non-biological technical features -- including variations in surgical/endoscopic techniques, laboratory procedures, and scanner hardware -- poses risks for clinical deployment. We present the first systematic investigation of pathology FM robustness to non-biological features. Our work (i) introduces measures to quantify FM robustness, (ii) demonstrates the consequences of limited robustness, and (iii) proposes a framework for FM robustification to mitigate these issues. Specifically, we developed PathoROB, a robustness benchmark with three novel metrics, including the robustness index, and four datasets covering 28 biological classes from 34 medical centers. Our experiments reveal robustness deficits across all 20 evaluated FMs, and substantial robustness differences between them. We found that non-robust FM representations can cause major diagnostic downstream errors and clinical blunders that prevent safe clinical adoption. Using more robust FMs and post-hoc robustification considerably reduced (but did not yet eliminate) the risk of such errors. This work establishes that robustness evaluation is essential for validating pathology FMs before clinical adoption and demonstrates that future FM development must integrate robustness as a core design principle. PathoROB provides a blueprint for assessing robustness across biomedical domains, guiding FM improvement efforts towards more robust, representative, and clinically deployable AI systems that prioritize biological information over technical artifacts.

Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting training data with LLM-synthesized rationales and applying supervised fine-tuning (SFT) to enhance reasoning ability, which in turn can improve downstream action prediction. However, the performance of such approaches remains inherently bounded by the reasoning capabilities of the model used to generate the rationales. In this paper, we introduce Shop-R1, a novel reinforcement learning (RL) framework aimed at enhancing the reasoning ability of LLMs for simulation of real human behavior in online shopping environments Specifically, Shop-R1 decomposes the human behavior simulation task into two stages: rationale generation and action prediction, each guided by distinct reward signals. For rationale generation, we leverage internal model signals (e.g., logit distributions) to guide the reasoning process in a self-supervised manner. For action prediction, we propose a hierarchical reward structure with difficulty-aware scaling to prevent reward hacking and enable fine-grained reward assignment. This design evaluates both high-level action types and the correctness of fine-grained sub-action details (attributes and values), rewarding outputs proportionally to their difficulty. Experimental results show that our method achieves a relative improvement of over 65% compared to the baseline.

Generative reward models with parallel sampling have enabled effective test-time scaling for reasoning tasks. Current approaches employ pointwise scoring of individual solutions or pairwise comparisons. However, pointwise methods underutilize LLMs' comparative abilities, while pairwise methods scale inefficiently with larger sampling budgets. We introduce GenSelect, where the LLM uses long reasoning to select the best solution among N candidates. This leverages LLMs' comparative strengths while scaling efficiently across parallel sampling budgets. For math reasoning, we demonstrate that reasoning models, such as QwQ and DeepSeek-R1-0528, excel at GenSelect, outperforming existing scoring approaches with simple prompting.

Service-level mobile traffic prediction for individual users is essential for network efficiency and quality of service enhancement. However, current prediction methods are limited in their adaptability across different urban environments and produce inaccurate results due to the high uncertainty in personal traffic patterns, the lack of detailed environmental context, and the complex dependencies among different network services. These challenges demand advanced modeling techniques that can capture dynamic traffic distributions and rich environmental features. Inspired by the recent success of diffusion models in distribution modeling and Large Language Models (LLMs) in contextual understanding, we propose an LLM-Enhanced Spatio-temporal Diffusion Model (LSDM). LSDM integrates the generative power of diffusion models with the adaptive learning capabilities of transformers, augmented by the ability to capture multimodal environmental information for modeling service-level patterns and dynamics. Extensive evaluations on real-world service-level datasets demonstrate that the model excels in traffic usage predictions, showing outstanding generalization and adaptability. After incorporating contextual information via LLM, the performance improves by at least 2.83% in terms of the coefficient of determination. Compared to models of a similar type, such as CSDI, the root mean squared error can be reduced by at least 8.29%. The code and dataset will be available at: https://github.com/SoftYuaneR/LSDM.

When using LLMs to rank items based on given criteria, or evaluate answers, the order of candidate items can influence the model's final decision. This sensitivity to item positioning in a LLM's prompt is known as position bias. Prior research shows that this bias exists even in large models, though its severity varies across models and tasks. In addition to position bias, LLMs also exhibit varying degrees of low repetition consistency, where repeating the LLM call with the same candidate ordering can lead to different rankings. To address both inconsistencies, a common approach is to prompt the model multiple times with different candidate orderings and aggregate the results via majority voting. However, this repetition strategy, significantly increases computational costs. Extending prior findings, we observe that both the direction -- favoring either the earlier or later candidate in the prompt -- and magnitude of position bias across instances vary substantially, even within a single dataset. This observation highlights the need for a per-instance mitigation strategy. To this end, we introduce a dynamic early-stopping method that adaptively determines the number of repetitions required for each instance. Evaluating our approach across three LLMs of varying sizes and on two tasks, namely re-ranking and alignment, we demonstrate that transitioning to a dynamic repetition strategy reduces the number of LLM calls by an average of 81%, while preserving the accuracy. Furthermore, we propose a confidence-based adaptation to our early-stopping method, reducing LLM calls by an average of 87% compared to static repetition, with only a slight accuracy trade-off relative to our original early-stopping method.

Foundation models pre-trained on massive datasets, including large language models (LLMs), vision-language models (VLMs), and large multimodal models, have demonstrated remarkable success in diverse downstream tasks. However, recent studies have shown fundamental limitations of these models: (1) limited representational capacity, (2) lower adaptability, and (3) diminishing scalability. These shortcomings raise a critical question: is Euclidean geometry truly the optimal inductive bias for all foundation models, or could incorporating alternative geometric spaces enable models to better align with the intrinsic structure of real-world data and improve reasoning processes? Hyperbolic spaces, a class of non-Euclidean manifolds characterized by exponential volume growth with respect to distance, offer a mathematically grounded solution. These spaces enable low-distortion embeddings of hierarchical structures (e.g., trees, taxonomies) and power-law distributions with substantially fewer dimensions compared to Euclidean counterparts. Recent advances have leveraged these properties to enhance foundation models, including improving LLMs' complex reasoning ability, VLMs' zero-shot generalization, and cross-modal semantic alignment, while maintaining parameter efficiency. This paper provides a comprehensive review of hyperbolic neural networks and their recent development for foundation models. We further outline key challenges and research directions to advance the field.

Contemporary database systems, while effective, suffer severe issues related to complexity and usability, especially among individuals who lack technical expertise but are unfamiliar with query languages like Structured Query Language (SQL). This paper presents a new database system supported by Artificial Intelligence (AI), which is intended to improve the management of data using natural language processing (NLP) - based intuitive interfaces, and automatic creation of structured queries and semi-structured data formats like yet another markup language (YAML), java script object notation (JSON), and application program interface (API) documentation. The system is intended to strengthen the potential of databases through the integration of Large Language Models (LLMs) and advanced machine learning algorithms. The integration is purposed to allow the automation of fundamental tasks such as data modeling, schema creation, query comprehension, and performance optimization. We present in this paper a system that aims to alleviate the main problems with current database technologies. It is meant to reduce the need for technical skills, manual tuning for better performance, and the potential for human error. The AI database employs generative schema inference and format selection to build its schema models and execution formats.

As artificial intelligence (AI) continues to evolve from a back-end computational tool into an interactive, generative collaborator, its integration into early-stage design processes demands a rethinking of traditional workflows in human-centered design. This paper explores the emergent paradigm of human-AI co-creation, where AI is not merely used for automation or efficiency gains, but actively participates in ideation, visual conceptualization, and decision-making. Specifically, we investigate the use of large language models (LLMs) like GPT-4 and multimodal diffusion models such as Stable Diffusion as creative agents that engage designers in iterative cycles of proposal, critique, and revision.

Advances in Large Language Models (LLMs) have led to a surge of LLM-powered applications. These applications have diverse token-generation latency requirements. As a result, simply classifying workloads as latency-sensitive (LS) or best-effort (BE) overlooks the nuances within the latency-sensitive category and results in suboptimal user experiences and scheduling opportunities. However, efficiently serving requests with multiple SLO requirements poses significant challenges. First, all requests within a batch generate new tokens simultaneously, which can misalign them with their distinct SLO requirements. Moreover, while existing systems focus on auto-scaling for handling various overall request rates, the diversity of SLOs necessitates fine-grained auto-scaling among these SLO tiers. Finally, unlike LS/BE scenarios, where BE requests can be aborted at any time to ensure the SLO attainment of LS requests, those with different latency-sensitive SLOs cannot tolerate prolonged delays, and tail latency must be controlled. To tackle these challenges, we propose PolyServe, a novel multi-SLO scheduling policy at scale that maintains high SLO attainment while maximizing throughput. PolyServe first groups requests into multiple bins based on their per-token latency requirement, then schedules each bin to a subset of the server fleet. PolyServe routes requests to the highest-load but still SLO-attainable server to create a load gradient that facilitates auto-scaling. To increase utilization, PolyServe permits looser-SLO requests to share tighter-SLO instances when their own servers are saturated. PolyServe uses profiling data to guide scheduling decisions and manage tail latency through request-wait-time-aware scheduling, dynamic chunking, and continuous chunked prefill prediction. PolyServe achieves 1.23x goodput gain compared to existing policies, achieving up to 92.5% of optimal goodput.

In August 2024, Bittensor's Subnet 9 (SN9) demonstrated that a distributed network of incentivized, permissionless actors could each pretrain large language models (LLMs) ranging from 700 million to 14 billion parameters, while surpassing established baselines. While that work validated blockchain-based decentralized pretraining as viable, it contained core issues: (i) every miner had to fit an entire model locally, and (ii) "winner-takes-all" rewards encouraged model hoarding. Here we introduce IOTA (Incentivized Orchestrated Training Architecture), an architecture that addresses these limitations by transforming SN9's previously isolated competitors into a single cooperating unit that can scale arbitrarily while still rewarding each contributor fairly. Key preliminary results: (1) Data- and Pipeline-parallel SWARM architecture - An orchestrator distributes model layers across heterogeneous miners and streams activations between them, enabling model sizes to scale with the number of participants rather than being constrained by the VRAM of a single machine; (2) Granular, continuous incentives - Validators measure each miner's contribution and allocate token emissions proportionally; (3) Activation compression - We used model-bottlenecks to cut communication bandwidths of activations by up to 128x, vastly improving training speed; (4) Butterfly All-Reduce - Miners average disjoint parameter slices in O(1) bandwidth, offering linear scalability, redundancy and built-in collusion detection; (5) CLASP (Contribution Loss Assessment via Sampling of Pathways) - A fair attribution scheme assigns credit to miners proportional to their marginal utility and detects exploits, even when contributions are interdependent across the pipeline.