KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models

Many real-world questions appear deceptively simple yet implicitly demand two capabilities: (i) systematic coverage of a bounded knowledge universe and (ii) compositional set-based reasoning over that universe, a phenomenon we term "the tip of the iceberg." We formalize this challenge through two orthogonal dimensions: knowledge width, the cardinality of the required universe, and reasoning depth, the number of compositional set operations. We introduce KnowledgeBerg, a benchmark of 4,800 multiple-choice questions derived from 1,183 enumeration seeds spanning 10 domains and 17 languages, with universes grounded in authoritative sources to ensure reproducibility. Representative open-source LLMs demonstrate severe limitations, achieving only 5.26-36.88 F1 on universe enumeration and 16.00-44.19 accuracy on knowledge-grounded reasoning. Diagnostic analyses reveal three stages of failure: completeness, or missing knowledge; awareness, or failure to identify requirements; and application, or incorrect reasoning execution. This pattern persists across languages and model scales. Although test-time compute and retrieval augmentation yield measurable gains -- up to 4.35 and 3.78 points, respectively -- substantial gaps remain, exposing limitations in how current LLMs organize structured knowledge and execute compositional reasoning over bounded domains. The dataset is available at https://huggingface.co/datasets/2npc/KnowledgeBerg

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas

It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings. Indeed, our experiments show that recent models -- with or without reasoning enabled -- consistently defect in single-shot social dilemmas. To tackle this safety concern, we present the first comparative study of game-theoretic mechanisms that are designed to enable cooperative outcomes between rational agents _in equilibrium_. Across four social dilemmas testing distinct components of robust cooperation, we evaluate the following mechanisms: (1) repeating the game for many rounds, (2) reputation systems, (3) third-party mediators to delegate decision making to, and (4) contract agreements for outcome-conditional payments between players. Among our findings, we establish that contracting and mediation are most effective in achieving cooperative outcomes between capable LLM models, and that repetition-induced cooperation deteriorates drastically when co-players vary. Moreover, we demonstrate that these cooperation mechanisms become _more effective_ under evolutionary pressures to maximize individual payoffs.

WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting

Time series foundation models (TSFMs) have recently achieved remarkable success in universal forecasting by leveraging large-scale pretraining on diverse time series data. Complementing this progress, incorporating frequency-domain information yields promising performance in enhancing the modeling of complex temporal patterns, such as periodicity and localized high-frequency dynamics, which are prevalent in real-world time series. To advance this direction, we propose a new perspective that integrates explicit frequency-domain representations into scalable foundation models, and introduce WaveMoE, a wavelet-enhanced mixture-of-experts foundation model for time series forecasting. WaveMoE adopts a dual-path architecture that jointly processes time series tokens and wavelet tokens aligned along a unified temporal axis, and coordinates them through a shared expert routing mechanism that enables consistent expert specialization while efficiently scaling model capacity. Preliminary experimental results on 16 diverse benchmark datasets indicate that WaveMoE has the potential to further improve forecasting performance by incorporating wavelet-domain corpora.

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization

Vision-Language Models (VLMs) are powerful but remain vulnerable to multimodal jailbreak attacks. Existing attacks mainly rely on either explicit visual prompt attacks or gradient-based adversarial optimization. While the former is easier to detect, the latter produces subtle perturbations that are less perceptible, but is usually optimized and evaluated under homogeneous open-source surrogate-target settings, leaving its effectiveness on commercial closed-source VLMs under heterogeneous settings unclear. To examine this issue, we study different surrogate-target settings and observe a consistent gap between homogeneous and heterogeneous settings, a phenomenon we term surrogate dependency. Motivated by this finding, we propose Mosaic, a Multi-view ensemble optimization framework for multimodal jailbreak against closed-source VLMs, which alleviates surrogate dependency under heterogeneous surrogate-target settings by reducing over-reliance on any single surrogate model and visual view. Specifically, Mosaic incorporates three core components: a Text-Side Transformation module, which perturbs refusal-sensitive lexical patterns; a Multi-View Image Optimization module, which updates perturbations under diverse cropped views to avoid overfitting to a single visual view; and a Surrogate Ensemble Guidance module, which aggregates optimization signals from multiple surrogate VLMs to reduce surrogate-specific bias. Extensive experiments on safety benchmarks demonstrate that Mosaic achieves state-of-the-art Attack Success Rate and Average Toxicity against commercial closed-source VLMs.

DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions

Accurately detecting and localizing hallucinations is a critical task for ensuring high reliability of image captions. In the era of Multimodal Large Language Models (MLLMs), captions have evolved from brief sentences into comprehensive narratives, often spanning hundreds of words. This shift exponentially increases the challenge: models must now pinpoint specific erroneous spans or words within extensive contexts, rather than merely flag response-level inconsistencies. However, existing benchmarks lack the fine granularity and domain diversity required to evaluate this capability. To bridge this gap, we introduce DetailVerifyBench, a rigorous benchmark comprising 1,000 high-quality images across five distinct domains. With an average caption length of over 200 words and dense, token-level annotations of multiple hallucination types, it stands as the most challenging benchmark for precise hallucination localization in the field of long image captioning to date. Our benchmark is available at https://zyx-hhnkh.github.io/DetailVerifyBench/.

Learning from Many and Adapting to the Unknown in Open-set Test Streams

Large Language Models (LLMs) generalize across tasks via reusable representations and flexible reasoning, yet remain brittle in real deployment under evolving tasks and continual distribution shift. A common approach is Test-Time Adaptation (TTA), existing ones of which updates models with hand-designed unsupervised objectives over the full parameter space and mostly overlook preserving shared source knowledge and the reliability of adaptation signals. Drawing on molecular signaling cascades of memory updating in Drosophila, we propose Synapse Consolidation (SyCo), a parameter-efficient LLM adaptation method that updates low-rank adapters through Rac1 and MAPK pathways under the guidance of a structured TTA objective driven by problem understanding, process understanding, and source-domain guardrail. Rac1 confines plasticity to a tail-gradient subspace that is less critical for source knowledge, enabling rapid specialization while preserving source representations. MAPK uses a tiered controller to suppress noisy updates and consolidate useful adaptations under non-stationary streams. To model real deployments with multiple sources and continually emerging tasks, we introduce Multi-source Open-set Adaptation (MOA) setting, where a model is trained on multiple labeled source tasks and then adapts on open, non-stationary unlabeled test streams that mix seen and unseen tasks with partial overlap in label and intent space. Across 18 NLP datasets and the MOA setting, SyCo consistently outperforms strong baselines, achieving 78.31\% on unseen-task adaptation and 85.37\% on unseen-data shifts.

Adapting SAM to Nuclei Instance Segmentation and Classification via Cooperative Fine-Grained Refinement

Nuclei instance segmentation is critical in computational pathology for cancer diagnosis and prognosis. Recently, the Segment Anything Model has demonstrated exceptional performance in various segmentation tasks, leveraging its rich priors and powerful global context modeling capabilities derived from large-scale pre-training on natural images. However, directly applying SAM to the medical imaging domain faces significant limitations: it lacks sufficient perception of the local structural features that are crucial for nuclei segmentation, and full fine-tuning for downstream tasks requires substantial computational costs. To efficiently transfer SAM's robust prior knowledge to nuclei instance segmentation while supplementing its task-aware local perception, we propose a parameter-efficient fine-tuning framework, named Cooperative Fine-Grained Refinement of SAM, consisting of three core components: 1) a Multi-scale Adaptive Local-aware Adapter, which enables effective capability transfer by augmenting the frozen SAM backbone with minimal parameters and instilling a powerful perception of local structures through dynamically generated, multi-scale convolutional kernels; 2) a Hierarchical Modulated Fusion Module, which dynamically aggregates multi-level encoder features to preserve fine-grained spatial details; and 3) a Boundary-Guided Mask Refinement, which integrates multi-context boundary cues with semantic features through explicit supervision, producing a boundary-focused signal to refine initial mask predictions for sharper delineation. These three components work cooperatively to enhance local perception, preserve spatial details, and refine boundaries, enabling SAM to perform accurate nuclei instance segmentation directly.

HYDRA: Unifying Multi-modal Generation and Understanding via Representation-Harmonized Tokenization

Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for generation. Existing approaches typically compromise by employing decoupled encoders, stacking representation encoder atop VAEs, or utilizing discrete quantization. However, these methods often disrupt information coherence and lead to optimization conflicts. To this end, we introduce HYDRA-TOK, a representation-harmonized pure ViT in the insight that visual modeling should evolve from generation to understanding. HYDRA-TOK reformulates the standard backbone into a progressive learner that transitions from a Gen-ViT, which captures structure-preserving primitives, to a Sem-ViT for semantic encoding. Crucially, this transition is mediated by a Generation-Semantic Bottleneck (GSB), which compresses features into a low-dimensional space to filter noise for robust synthesis, then restores dimensionality to empower complex semantic comprehension. Built upon this foundation, we present HYDRA, a native unified framework integrating perception and generation within a single parameter space. Extensive experiments establish HYDRA as a new state-of-the-art. It sets a benchmark in visual reconstruction (rFID 0.08) and achieves top-tier generation performance on GenEval (0.86), DPG-Bench (86.4), and WISE (0.53), while simultaneously outperforming previous native UMMs by an average of 10.0 points across eight challenging understanding benchmarks.

Bringing Model Editing to Generative Recommendation in Cold-Start Scenarios

Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existing GR models suffer from severe cold-start collapse: their recommendation accuracy on cold-start items can drop to near zero. Current solutions typically rely on retraining with cold-start interactions, which is hindered by sparse feedback, high computational cost, and delayed updates, limiting practical utility in rapidly evolving recommendation catalogs. Inspired by model editing in NLP, which enables training-free knowledge injection into large language models, we explore how to bring this paradigm to generative recommendation. This, however, faces two key challenges: GR lacks the explicit subject-object binding common in natural language, making targeted edits difficult; and GR does not exhibit stable token co-occurrence patterns, making the injection of multi-token item representations unreliable. To address these challenges, we propose GenRecEdit, a model editing framework tailored for generative recommendation. GenRecEdit explicitly models the relationship between the full sequence context and next-token generation, adopts iterative token-level editing to inject multi-token item representations, and introduces a one-to-one trigger mechanism to reduce interference among multiple edits during inference. Extensive experiments on multiple datasets show that GenRecEdit substantially improves recommendation performance on cold-start items while preserving the model's original recommendation quality. Moreover, it achieves these gains using only about 9.5% of the training time required for retraining, enabling more efficient and frequent model updates.

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system limitations such as perception latency and lack of common sense knowledge can lead to dangerous errors. Current safety evaluations, often restricted to static images, text, or general hazards, fail to adequately benchmark dynamic unsafe action detection in these specific contexts. To bridge this gap, we introduce \textbf{HomeSafe-Bench}, a challenging benchmark designed to evaluate Vision-Language Models (VLMs) on unsafe action detection in household scenarios. HomeSafe-Bench is contrusted via a hybrid pipeline combining physical simulation with advanced video generation and features 438 diverse cases across six functional areas with fine-grained multidimensional annotations. Beyond benchmarking, we propose \textbf{Hierarchical Dual-Brain Guard for Household Safety (HD-Guard)}, a hierarchical streaming architecture for real-time safety monitoring. HD-Guard coordinates a lightweight FastBrain for continuous high-frequency screening with an asynchronous large-scale SlowBrain for deep multimodal reasoning, effectively balancing inference efficiency with detection accuracy. Evaluations demonstrate that HD-Guard achieves a superior trade-off between latency and performance, while our analysis identifies critical bottlenecks in current VLM-based safety detection.