From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts. We observe two distinct entropy patterns among attention heads: Rigid Heads, whose entropy stays near zero across input segments, and Dynamic Heads, whose entropy fluctuates significantly. Crucially, the distribution of these types is context-dependent and cannot be predetermined offline. We therefore propose EntropyInfer, a training-free framework that uses attention entropy to adaptively allocate compute at the granularity of individual heads and segments during prefilling. For decoding, we introduce a latent KV cache compression scheme that leverages generated output tokens, rather than prefill tokens alone, to identify and retain the most critical cache entries. Extensive experiments on Llama, Qwen and openPangu model series show that EntropyInfer consistently outperforms baselines including SnapKV, AdaKV, and CritiPrefill, achieving up to 2.39$\times$ end-to-end speedup beyond 100k tokens with minimal quality degradation compared to full attention. The code is released in https://github.com/SHA-4096/EntropyInfer.

Event-driven dynamic trajectories reconstruction and measurement of mechanical parameters for fragments

During warhead detonation, high-density, high-speed, and mutually occluded fragments are generated. Their mechanical parameters (position, velocity, kinetic energy) directly determine the lethality of the warhead fragment field. However, high-intensity flash and smoke in detonation scenarios severely hinder the accurate acquisition of these mechanical parameters. To address this challenge, this paper integrates experimental mechanics approaches and presents an event-driven method for reconstructing the dynamic trajectories of fragments and measuring their mechanical parameters. As a novel brain-inspired visual sensor, event cameras offer microsecond-level temporal resolution and high dynamic range lighting change perception, overcoming the difficulty of accurately measuring high-speed targets under strong flash interference. The method constructs a multi-event-camera vision system, adopting three geometric constraints: time-correlated epipolar constraint to find potential matching event point pairs, and trifocal tensor line constraint plus local homography constraint to eliminate mismatches. A comprehensive probability model is established, with entropy weight method determining the weight of each constraint's probability to quantitatively filter mismatches. 3D trajectory reconstruction is achieved via spatial line-line intersection and nonlinear optimization. Finally, the velocity and kinetic energy of the fragments are calculated based on the reconstructed trajectory. This method provides reliable technical support for the mechanical damage evaluation of warhead fragment fields and the tactical protection design.

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making them increasingly central to enterprise analytics. This integration introduces new security vulnerabilities across data resources, database execution, and agent reasoning, recombining concerns from database security and general-purpose LLM-agent security into failure modes that neither line of work captures on its own. To address this gap, we present a systematic security study of data agents. Our contributions are threefold. First, we develop a layered vulnerability framework that identifies eight data agent-specific risks across interpretation, execution, and policy layers. Second, we introduce an attack taxonomy organized by adversary goal, tactic, and technique, covering three goals, seven tactics, and fourteen techniques, and pair it with an LLM-driven payload generation pipeline grounded in real database schemas. Third, we evaluate these attacks on six systems, including four open-source data agents and two production cloud analytics services. Our experiments reveal substantial security vulnerabilities across current systems and yield four key takeaways.

QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving

Retrieval-augmented generation (RAG) improves large language model (LLM) answer quality by grounding generation in external evidence, but processing retrieved contexts makes the prefill stage a dominant serving cost. RAG cache fusion reduces this cost by reusing precomputed key-value (KV) caches for retrieved chunks and selectively recomputing tokens under the current prompt. Existing selectors, however, face a dilemma between quality and efficiency: fast query-agnostic or final-layer query-to-context selectors can miss request-relevant evidence, whereas full-view query-aware selectors require broad context and layer visibility before recomputation and therefore stall the layer-wise cache-fusion pipeline. We present QCFuse, a compressed-view query-aware selector for RAG cache fusion. QCFuse uses chunk-anchor query probing to condition user-query states on compact per-chunk anchors and critical-layer profiling to identify recomputation tokens without all-layer inspection. We implement QCFuse in SGLang and evaluate it on four open-weight LLMs across six datasets. QCFuse reaches full-prefill-level quality. At matched quality, QCFuse achieves an average prefill-time speedup of 1.7x over full prefill and 1.5x over ProphetKV, the strongest quality-preserving baseline.

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)

Purpose: To develop an interpretable and trustworthy AI framework that combines deep learning based MRI Osteoarthritis Knee Score (MOAKS) prediction with interpretable statistical modeling to study structure-pain relationships at scale using data from the Osteoarthritis Initiative (OAI). Materials and Methods: We first developed a deep learning framework to predict MOAKS features directly from knee MRIs and incorporated conformal prediction to provide prediction uncertainty quantification. This uncertainty-aware strategy enables explicit filtering of model outputs, retaining only high-confidence MOAKS predictions at the knee level. Second, we applied a longitudinal latent class mixed model (LCMM) to examine associations between key structural abnormalities and four complementary knee pain measurements. Results: Among the three MRI-defined abnormalities (i.e., bone marrow lesions (BML), cartilage loss (CART), and meniscal extrusion (ME)), our framework substantially improved the Matthews correlation coefficient (MCC) and some other metrics. For example, MCC increased from 0.69 to 0.91 for BML, from 0.45 to 0.80 for CART, and from 0.59 to 0.89 for ME. Using these high-confidence predictions, we expanded the sample size to 2,175 knees for the LCMM analysis. Two distinct pain trajectories were identified (rapid and stable pain progression). The estimated odds ratios (95% CI) for the rapid progression group were 1.62 (1.12-2.35) for BML, 1.83 (1.24-2.70) for CART loss, and 2.50 (1.75-3.57) for ME. Conclusion: These results highlight the importance of these structural abnormalities as risk factors for pain and functional progression in osteoarthritis.

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path. This paradigm has greatly improved training speed, but it has also encouraged a default assumption that efficient training requires physics to reside on the GPU. We revisit this assumption. Our view is that, in simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop. We present UniLab, a heterogeneous CPU-simulation / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization. UniLab is implemented as a complete and extensible training system using MuJoCoUni and MotrixSim CPU-batched physics backends, supporting PPO, FastSAC, FlashSAC, and APPO. On representative simulation-based robot control tasks, UniLab improves end-to-end training efficiency by 3--10$\times$ under the same hardware configuration, while reducing dependence on the NVIDIA CUDA-based software stack and supporting cross-platform execution on the Apple macOS platform and the AMD ROCm and Intel XPU accelerator backends. These results show that GPU simulation is an effective path to efficient training, but not a necessary one, broadening the practical system choices available for robot RL training. Project page: https://unilabsim.github.io.

A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path. This paradigm has greatly improved training speed, but it has also encouraged a default assumption that efficient training requires physics to reside on the GPU. We revisit this assumption. Our view is that, in simulation-dominated robot control, the essential question is not which processor runs physics, but whether simulation throughput, policy learning, and runtime synchronization form an efficient end-to-end loop. We present UniLab, a heterogeneous CPU-simulation / GPU-learning architecture that decouples CPU-parallel simulation from GPU policy updates through a unified runtime for data movement, buffering, and synchronization. UniLab is implemented as a complete and extensible training system using MuJoCoUni and MotrixSim CPU-batched physics backends, supporting PPO, SAC, FlashSAC, TD3, and APPO. On representative simulation-based robot control tasks, UniLab improves end-to-end training efficiency by 3--10$\times$ under the same hardware configuration, while reducing dependence on the NVIDIA CUDA-based software stack and supporting cross-platform execution on the Apple macOS platform and the AMD ROCm and Intel XPU accelerator backends. These results show that GPU simulation is an effective path to efficient training, but not a necessary one, broadening the practical system choices available for robot RL training. Project page: https://github.com/unilabsim/UniLab.

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In this work, we study whether heterogeneous embodied decision-making problems can be unified within a single vision-language-action model. We present Qwen-VLA, a unified embodied foundation model that extends Qwen's vision-language modeling stack from perception, understanding, and reasoning to continuous action and trajectory generation through a DiT-based action decoder. Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data, trajectory-centric supervision, and auxiliary vision-language data. To support multiple robot platforms, we introduce embodiment-aware prompt conditioning, where robot-specific textual descriptions specify the current embodiment and control convention. We further cast manipulation, navigation, and trajectory prediction into a unified action-and-trajectory prediction framework, enabling transferable visual grounding, spatial reasoning, and continuous action generation across robot morphologies, task families, and environments. Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot embodiment. Qwen-VLA-Instruct achieves 97.9% on LIBERO, 73.7% on Simpler-WidowX, 86.1%/87.2% on RoboTwin-Easy/Hard, 69.0% OSR on R2R, 59.6% SR on RxR, 76.9% average OOD success in real-world ALOHA experiments, and 26.6% zero-shot success on DOMINO dynamic manipulation.

Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting

Local temporal patterns in real-world time series continuously shift, rendering globally shared transformations suboptimal. Current deep forecasting models, despite their scale and complexity, rely on fixed weight matrices applied uniformly to all temporal tokens. This creates a static pattern response: models settle into a compromised average, unable to adapt to changing local dynamics. We introduce Dynamic Pattern Recalibration (DPR), a backbone-agnostic mechanism that resolves this via token-level recalibration. Through a lightweight "Perceive-Route-Modulate" pipeline, DPR computes a soft-routing distribution over a learned basis of adaptive response patterns, generating a time-aware modulation vector that recalibrates hidden states via a residual Hadamard product. As a backbone-agnostic adapter, DPR enhances forecasting across diverse architectures with minimal overhead, confirming it addresses a general bottleneck. As a minimalist standalone model, DPRNet achieves competitive performance across 12 benchmarks, validating dynamic recalibration against macroscopic parameter scaling.