arXiv:2608.27875v2 Announce Type: replace Abstract: Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module often introduces large errors at very low bit-widths, causing performance degradation. Existing methods mainly rely on smoothing techniques to handle outliers, while we propose a hybrid quantization design to better balance accuracy and efficiency. Specifically, we propose \textbf{HyQuant}, an efficient hybrid quantization framework for LLM attention. HyQuant quantizes most attention states into low-bit formats while retaining a small set of vertical-line tokens and local-window states in high precision. These accuracy-critical regions are selected using lightweight vertical-line-aware attention-pattern signals, reducing quantization error with limited overhead. In the Prefill stage, HyQuant uses a hybrid-precision quantized attention operator that preserves vertical-line tokens and a local sliding window in full precision while quantizing the remaining context. In the Decode stage, HyQuant applies the same principle to KV-cache compression and fuses KV dequantization with attention computation to improve memory and hardware efficiency. Across diverse tasks, models, and datasets, HyQuant maintains nearly lossless accuracy with an extremely simple design, demonstrating the efficiency and practical feasibility of hybrid quantization for LLM attention. Code is available at: https://github.com/jerrysfls/HyQuant .

arXiv:2609.10441v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context limits. To address this, sequential approaches like MemAgent extend the effective context by reading text in segments and iteratively updating a fixed-size memory. However, this sequential paradigm suffers from high latency and requires costly reinforcement learning (RL) training, which can lead to overfitting on specific datasets. To overcome these limitations, we propose ConvMem, a training-free, highly parallelizable framework that reformulates long-context reasoning as a hierarchical convolution. Inspired by CNNs, ConvMem treats an LLM prompted with a specific query as a convolutional kernel. This kernel summarizes text segments hierarchically, shortening the reasoning path from a linear chain into a logarithmic tree. Specifically, ConvMem integrates \textit{Configurable Strides} and \textit{Skip Connections} to ensure robust evidence capture and propagation, while employing \textit{Multi-Kernel Convolution} to decompose complex queries into disentangled semantic channels. This design not only mitigates error accumulation but also enables massive parallelization across both text segments and reasoning threads. Experiments on RULER-HotpotQA and RULER-2WikiMultiHopQA demonstrate that ConvMem outperforms training-free baselines and avoids the risk of overfitting to parametric priors often observed in RL-trained models on out-of-distribution tasks.

Ancient DNA from 149 individuals at 11 sites in Gansu, China, dated to around 4,700–3,000 years ago, reveals human population history during early transcontinental exchanges of agriculture and technology, as well as contemporary social practices, at the large Mogou cemetery.

arXiv:2605.24636v2 Announce Type: new Abstract: While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios remain critically underexplored, particularly in dentistry. Here we introduce GlobalDentBench, the first multinational dental benchmark, featuring a taxonomy that encompasses 14 dental specialties across 88 countries and regions spanning six continents. The benchmark comprises 8,978 expert-validated questions across three formats (multiple-choice, short-answer, and case-based questions) and assesses three progressive reasoning levels: knowledge recall (L1), routine reasoning (L2), and individualized reasoning (L3). To ensure data quality, the automated construction framework was calibrated by six senior dentists, achieving expert agreement rates of 99.98% for multiple-choice and short-answer questions and 96.78% for the more complex case-based questions. Evaluation of 12 frontier LLMs on GlobalDentBench revealed a sharp, stepwise performance degradation with increasing reasoning complexity. Specifically, accuracy plummeted from 81.34% on multiple-choice to 64.53% on short-answer and 22.34% on case-based questions, while declining markedly from 74.01% at L1 to 55.64% at L2 and 35.71% at L3. More critically, risk analysis of real-world dental cases demonstrated an alarming overall unsafe rate of 31.01% in LLM-generated clinical recommendations, with 4.51% posing risks of irreversible patient harm and risks particularly pronounced in specialties such as orthodontics. These findings expose fundamental limitations in the medical reasoning and safety of current LLMs. Consequently, GlobalDentBench provides a scalable foundation for trustworthy clinical AI evaluation, underscoring the urgent need for rigorous validation before the safe deployment of these models in healthcare.

arXiv:2605.25389v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools, the implicit trust in tool outputs creates a critical attack surface. Existing tool attacks are limited by domain specificity or fixed and static templates. To address these challenges, we propose Evo-Attacker, which formulates the tool attack as a self-evolving, memory-augmented reinforcement learning process. Evo-Attacker constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns and strategize modifying interventions at critical moments. Furthermore, we introduce Attack-Flow GRPO to optimize intermediate reasoning steps via terminal outcomes, addressing the long-horizon credit assignment challenge. Comprehensive experiments demonstrate that Evo-Attacker consistently outperforms baselines, highlighting its generalization and evolutionary capabilities and the urgent need for defensive tool safeguards.

arXiv:2604.27636v2 Announce Type: replace Abstract: Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimensional energy landscapes. Deep generative models offer efficient structure sampling, yet their outputs remain shaped by training data and can underexplore minima that are rare but physically relevant. We introduce generative structure search (GSS), a unified framework that formulates diffusion-based generation and random structure search (RSS) as limiting regimes of a common sampling process driven by learned score fields and physical forces. Coupling these drivers lets GSS use data priors to accelerate sampling while retaining energy-guided exploration of local minima. Across molecular and crystalline systems, GSS recovers diverse metastable structures with more than tenfold lower sampling cost than RSS for broad coverage and remains effective for compositions outside the training distribution. The results establish a physically grounded generative search strategy for discovering structures beyond the reach of data-driven sampling alone.

arXiv:2510.05699v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant challenges, including mislabeled samples, distribution shifts, and discrepancies in model size between experimental and real-world settings. To address these limitations, we introduce tokenizers as a new attack vector for membership inference. Specifically, a tokenizer converts raw text into tokens for LLMs. Unlike full models, tokenizers can be efficiently trained from scratch, thereby avoiding the aforementioned challenges. In addition, the tokenizer's training data is typically representative of the data used to pre-train LLMs. Despite these advantages, the potential of tokenizers as an attack vector remains unexplored. To this end, we present the first study on membership leakage through tokenizers and explore five attack methods to infer dataset membership. Extensive experiments on millions of Internet samples reveal the vulnerabilities in the tokenizers of state-of-the-art LLMs. To mitigate this emerging risk, we further propose an adaptive defense. Our findings highlight tokenizers as an overlooked yet critical privacy threat, underscoring the urgent need for privacy-preserving mechanisms specifically designed for them.

arXiv:2604.03630v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables gene expression mapping within anatomical context but remains costly and low-throughput. Hematoxylin and eosin (H\&E) staining offers rich morphology yet lacks molecular resolution. We present \textbf{\ours} (\textbf{S}patial \textbf{T}ranscriptomics and hist\textbf{O}logy \textbf{R}epresentation \textbf{M}odel), a foundation model trained on 1.2 million spatially resolved transcriptomic profiles with matched histology across 18 organs. Using a hierarchical architecture integrating morphological features, gene expression, and spatial context, STORM bridges imaging and omics through robust molecular--morphological representations. STORM enhances spatial domain discovery, producing biologically coherent tissue maps, and outperforms existing methods in predicting spatial gene expression from H\&E images across 11 tumor types. The model is platform-agnostic, performing consistently across Visium, Xenium, Visium HD, and CosMx. Applied to 23 independent cohorts comprising 7,245 patients, STORM significantly improves immunotherapy response prediction and prognostication over established biomarkers, providing a scalable framework for spatially informed discovery and clinical precision medicine.

arXiv:2604.03925v1 Announce Type: cross Abstract: Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user interaction data, limiting their applicability in privacy-conscious settings. We propose AdaptFuse, a training-free framework that externalizes probabilistic computation entirely from the LLM: a symbolic module maintains a Bayesian posterior over a discrete hypothesis set, while a frozen LLM contributes semantic reasoning via multi-sample Dirichlet aggregation. The two signals are combined through entropy-adaptive fusion, which automatically weights each source by its predictive confidence, shifting reliance from the LLM to the symbolic posterior as evidence accumulates. We evaluate across three domains: flight recommendation, hotel recommendation, and web shopping; on Gemma 2 9B, Llama 3 8B, and Qwen 2.5 7B. AdaptFuse consistently outperforms both prompting baselines and fine-tuned Bayesian Teaching models on all tasks, with accuracy improving monotonically over interaction rounds. These results demonstrate that principled inference-time algorithms can substitute for fine-tuning in personalized recommendation, without storing or training on sensitive user data. All the code and materials will be open-sourced.

arXiv:2509.12626v3 Announce Type: replace-cross Abstract: Aligning agentic AI with user intent is critical for delegating complex, socially embedded tasks, yet user preferences are often implicit, evolving, and difficult to specify upfront. We present DoubleAgents, a system for human-agent alignment in coordination tasks, grounded in distributed cognition. DoubleAgents integrates three components: (1) a coordination agent that maintains state and proposes plans and actions, (2) a dashboard visualization that makes the agent's reasoning legible for user evaluation, and (3) a policy module that transforms user edits into reusable alignment artifacts, including coordination policies, email templates, and stop hooks, which improve system behavior over time. We evaluate DoubleAgents through a two-day lab study (n=10), three real-world deployments, and a technical evaluation. Participants' comfort in offloading tasks and reliance on DoubleAgents both increased over time, correlating with the three distributed cognition components. Participants still required control at points of uncertainty - edge-case flagging and context-dependent actions. We contribute a distributed cognition approach to human-agent alignment in socially embedded tasks.

arXiv:2406.09031v5 Announce Type: replace-cross Abstract: Graph pooling has gained attention for its ability to obtain effective node and graph representations for various downstream tasks. Despite the recent surge in graph pooling approaches, there is a lack of standardized experimental settings and fair benchmarks to evaluate their performance. To address this issue, we have constructed a comprehensive benchmark that includes 17 graph pooling methods and 28 different graph datasets. This benchmark systematically assesses the performance of graph pooling methods in three dimensions, i.e., effectiveness, robustness, and generalizability. We first evaluate the performance of these graph pooling approaches across different tasks including graph classification, graph regression and node classification. Then, we investigate their performance under potential noise attacks and out-of-distribution shifts in real-world scenarios. We also involve detailed efficiency analysis, backbone analysis, parameter analysis and visualization to provide more evidence. Extensive experiments validate the strong capability and applicability of graph pooling approaches in various scenarios, which can provide valuable insights and guidance for deep geometric learning research. The source code of our benchmark is available at https://github.com/goose315/Graph_Pooling_Benchmark.

arXiv:2603.22779v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are equipped with profound semantic knowledge, making them a natural choice for injecting semantic generalization into personalized search systems. However, in practice we find that directly fine-tuning LLMs on industrial personalized tasks (e.g. next item prediction) often yields suboptimal results. We attribute this bottleneck to a critical Knowledge--Action Gap: the inherent conflict between preserving pre-trained semantic knowledge and aligning with specific personalized actions by discriminative objectives. Empirically, action-only training objectives induce Semantic Collapse, such as attention "sinks". This degradation severely cripples the LLM's generalization, failing to bring improvements to personalized search systems. We propose KARMA (Knowledge--Action Regularized Multimodal Alignment), a unified framework that treats semantic reconstruction as a train-only regularizer. KARMA optimizes a next-interest embedding for retrieval (Action) while enforcing semantic decodability (Knowledge) through two complementary objectives: (i) history-conditioned semantic generation, which anchors optimization to the LLM's native next-token distribution, and (ii) embedding-conditioned semantic reconstruction, which constrains the interest embedding to remain semantically recoverable. On Taobao search system, KARMA mitigates semantic collapse (attention-sink analysis) and improves both action metrics and semantic fidelity. In ablations, semantic decodability yields up to +22.5 HR@200. With KARMA, we achieve +0.25 CTR AUC in ranking, +1.86 HR in pre-ranking and +2.51 HR in recalling. Deployed online with low inference overhead at ranking & pre-ranking stage, KARMA drives +0.9% increase in GMV.

arXiv:2603.22978v1 Announce Type: new Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as images to be directly processed by large language models, which can assist in tracking and analyzing malfunctions, we propose a novel textual representation of fault trees. Building on it, we construct a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments, evaluating a model's ability to assist in malfunction localization, which contains $3130$ entries and $40.75$ turns per entry on average. We train an end-to-end model to generate vague information to reflect user behavior and introduce long-range rollback and recovery procedures to simulate user error scenarios, enabling assessment of a model's integrated capabilities in task tracking and error recovery, and Gemini 2.5 pro archives the best performance.

arXiv:2603.22369v1 Announce Type: cross Abstract: Accurate prediction of synthetic lethality (SL) is important for guiding the development of cancer drugs and therapies. SL prediction faces significant challenges in the effective fusion of heterogeneous multi-source data. Existing multimodal methods often suffer from "modality laziness" due to disparate convergence speeds, which hinders the exploitation of complementary information. This is also one reason why most existing SL prediction models cannot perform well on both pan-cancer and single-cancer SL pair prediction. In this study, we propose SynLeaF, a dual-stage multimodal fusion framework for SL prediction across pan- and single-cancer contexts. The framework employs a VAE-based cross-encoder with a product of experts mechanism to fuse four omics data types (gene expression, mutation, methylation, and CNV), while simultaneously utilizing a relational graph convolutional network to capture structured gene representations from biomedical knowledge graphs. To mitigate modality laziness, SynLeaF introduces a dual-stage training mechanism employing featurelevel knowledge distillation with adaptive uni-modal teacher and ensemble strategies. In extensive experiments across eight specific cancer types and a pancancer dataset, SynLeaF achieves superior performance in 17 out of 19 scenarios. Ablation studies and gradient analyses further validate the critical contributions of the proposed fusion and distillation mechanisms to model robustness and generalization. To facilitate community use, a web server is available at https://synleaf.bioinformatics-lilab.cn.

arXiv:2603.22779v1 Announce Type: cross Abstract: Large Language Models (LLMs) are equipped with profound semantic knowledge, making them a natural choice for injecting semantic generalization into personalized search systems. However, in practice we find that directly fine-tuning LLMs on industrial personalized tasks (e.g. next item prediction) often yields suboptimal results. We attribute this bottleneck to a critical Knowledge--Action Gap: the inherent conflict between preserving pre-trained semantic knowledge and aligning with specific personalized actions by discriminative objectives. Empirically, action-only training objectives induce Semantic Collapse, such as attention ``sinks''. This degradation severely cripples the LLM's generalization, failing to bring improvements to personalized search systems. We propose KARMA (Knowledge--Action Regularized Multimodal Alignment), a unified framework that treats semantic reconstruction as a train-only regularizer. KARMA optimizes a next-interest embedding for retrieval (Action) while enforcing semantic decodability (Knowledge) through two complementary objectives: (i) history-conditioned semantic generation, which anchors optimization to the LLM's native next-token distribution, and (ii) embedding-conditioned semantic reconstruction, which constrains the interest embedding to remain semantically recoverable. On Taobao search system, KARMA mitigates semantic collapse (attention-sink analysis) and improves both action metrics and semantic fidelity. In ablations, semantic decodability yields up to +22.5 HR@200. With KARMA, we achieve +0.25 CTR AUC in ranking, +1.86 HR in pre-ranking and +2.51 HR in recalling. Deployed online with low inference overhead at ranking stage, KARMA drives +0.5% increase in Item Click.

arXiv:2603.01875v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a homogeneous training backend (e.g., FSDP and DeepSpeed) for both models, leading to suboptimal training efficiency. In this paper, we present a novel framework for LLM distillation, termed \textbf{KDFlow}, which features a decoupled architecture and employs SGLang for teacher inference. By bridging the training efficiency of FSDP2 and the inference efficiency of SGLang, KDFlow achieves full utilization of both advantages in a unified system. Moreover, instead of transferring full logits across different processes, our framework only transmits the teacher's hidden states using zero-copy data transfer and recomputes the logits on the student side, effectively balancing the communication cost and KD performance. Furthermore, our framework supports both off-policy and on-policy distillation and incorporates KD algorithms for cross-tokenizer KD through highly extensible and user-friendly APIs. Experiments show that KDFlow can achieve \textbf{1.44$\times$ to 6.36$\times$} speedup compared to current KD frameworks, enabling researchers to rapidly prototype and scale LLM distillation with minimal engineering overhead. Code is available at: https://github.com/songmzhang/KDFlow

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10258-4

Colonic stem cells retain a memory of inflammation following disease resolution and there is a mechanistic link between chronic inflammation and malignancy, suggesting potential strategies to mitigate cancer risk in patients with chronic inflammatory conditions.

arXiv:2603.12612v1 Announce Type: cross Abstract: Scaling Maximum Entropy Reinforcement Learning (RL) to high-dimensional humanoid control remains a formidable challenge, as the ``curse of dimensionality'' induces severe exploration inefficiency and training instability in expansive action spaces. Consequently, recent high-throughput paradigms have largely converged on deterministic policy gradients combined with massive parallel simulation. We challenge this compromise with FastDSAC, a framework that effectively unlocks the potential of maximum entropy stochastic policies for complex continuous control. We introduce Dimension-wise Entropy Modulation (DEM) to dynamically redistribute the exploration budget and enforce diversity, alongside a continuous distributional critic tailored to ensure value fidelity and mitigate high-dimensional value overestimation. Extensive evaluations on HumanoidBench and other continuous control tasks demonstrate that rigorously designed stochastic policies can consistently match or outperform deterministic baselines, achieving notable gains of 180\% and 400\% on the challenging \textit{Basketball} and \textit{Balance Hard} tasks.

arXiv:2603.06651v1 Announce Type: cross Abstract: Euclidean gradient descent algorithms barely capture the geometry of objective function-induced hypersurfaces and risk driving update trajectories off the hypersurfaces. Riemannian gradient descent algorithms address these issues but fail to represent complex hypersurfaces via a single classic manifold. We propose geodesic gradient descent (GGD), a generic and learning-rate-free Riemannian gradient descent algorithm. At each iteration, GGD uses an n-dimensional sphere to approximate a local neighborhood on the objective function-induced hypersurface, adapting to arbitrarily complex geometries. A tangent vector derived from the Euclidean gradient is projected onto the sphere to form a geodesic, ensuring the update trajectory stays on the hypersurface. Parameter updates are performed using the endpoint of the geodesic. The maximum step size of the gradient in GGD is equal to a quarter of the arc length on the n-dimensional sphere, thus eliminating the need for a learning rate. Experimental results show that compared with the classic Adam algorithm, GGD achieves test MSE reductions ranging from 35.79% to 48.76% for fully connected networks on the Burgers' dataset, and cross-entropy loss reductions ranging from 3.14% to 11.59% for convolutional neural networks on the MNIST dataset.