Real-world harness engineering is driven by explicit and implicit user requirements, which guide development and validation. However, existing harness evolution methods often overlook implicit requirements and interaction needs, while using a single evolution agent to modify the harness and benchmark scores to select changes. This process often produces narrow patches and leads to benchmark-specific local optima. We introduce Agentic Harness Engineering Beta (AHE-Beta), a requirement-centered loop that brings real-world engineering practices into harness evolution. The loop consists of three steps: (1) User-driven evaluation lets simulated users raise their requirements as issues while they work with the harness over multiple turns. (2) Team-based modification implements those requirements as generalizable changes rather than task-specific patches. (3) Requirement-driven selection merges a change only when it resolves a verified requirement and passes review. Empirically, on held-out tasks, AHE-Beta raises pass@1 from 21.9% to 33.3% while using 40.8% fewer tokens than Base Harness, and achieves higher pass@1 than Claude Code, Meta-Harness, and AHE. In a blind human A/B test, real users prefer AHE-Beta in 31 of 48 valid pairs and rate it higher on all five dimensions, matching the directional preference of the user simulator. The human A/B results show that AHE-Beta achieves its goal of aligning harness evolution with real-world user requirements. Without further evolution, the gains transfer to GLM-5.3 and DeepSeek-V4.1-Flash with pass@1 improvements of 15.8% and 5.3% over Base Harness. Together, these results show that requirement-centered harness evolution is a more general method for improving agent capabilities.
When shown matches between two photographs of the same cathedral, people can tell at a glance which ones are wrong: a window matched to its look-alike jumps against its neighbors, while correct matches shift together. Two-view correspondence learning, also called correspondence pruning, asks a network to make this judgment for thousands of candidate matches, most of which are wrong. Mamba, a fast sequence model, now drives strong pruners, but it reads the matches as a plain sequence, and whether its scan can capture such agreement is unclear. We propose SFMambaNet, which scans the matches cluster by cluster, so that correct matches vary slowly along the sequence while wrong ones stay erratic, and filters the scanned features with learnable frequency-domain gates between its forward and backward passes. On camera pose estimation, outlier removal and homography estimation, we find that SFMambaNet outperforms spatial-domain Mamba baselines with about two million parameters. Contrary to the usual expectation that such gains come from extra capacity, we find that a parameter-free low-pass filter beats point-wise layers as large as the gates. The learned gates turn low-pass on their own and make the scan far less sensitive to how the matches are shuffled. Together, these results show that frequency is a natural language for describing agreement between correspondences, with implications for other sequence models that must read unordered sets, such as point clouds and graphs.
For robots to assist, serve, and collaborate with humans, they must not only interpret human requests conveyed through language and multimodal intentional cues, but also execute long-horizon tasks that interleave navigation and manipulation. In this paper, we introduce HEIR, a resource for studying how to Harness Egocentric Intent for Human-Robot Interaction. HEIR pairs human speech, measured gaze, and egocentric video with robot observations and teleoperated navigation-manipulation trajectories, while each session preserves successive episodes, with each request fulfilled through multiple execution subtasks. The captured data, together with human-authored annotations, support the study of intent grounding, execution planning, and task completion within a unified interaction setting. To demonstrate the value of HEIR, we conduct extensive offline experiments to evaluate how models benefit from additional human-centric context across these tasks, together with real-robot experiments that assess execution task completion. HEIR thus provides a valuable resource for studying user-centric robot interaction in naturalistic household environments. Our demo and dataset are available online.
This report summarizes the Mobile Unified Multimodal Understanding (MUMU) track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. MUMU asks for a single unified model that jointly performs multi-concept image tagging over quality, scene, and event vocabularies, open-vocabulary object detection, and concise image captioning, within a budget of 0.5B parameters and 8 GB of peak inference memory. Submissions are ranked by a weighted task score scaled by an efficiency factor. We describe the tasks, rules, and evaluation protocol, report the final results, and review the methods of the top three teams. All three leading solutions build on the compact Florence-2-base model, but extend it in different ways: lightweight tagging heads with cross-task inference refinement, a shared low-rank adapter trained on coverage-aware multi-source data with task-dependent decoding, and a training-free pipeline that maps captions to tags and applies detection test-time augmentation. The results show that a compact prompt-based vision-language model can serve all three outputs when supervision, decoding, and cross-task cues are designed for each task, while open-vocabulary detection on novel categories remains the main bottleneck.
Recommender systems, which retrieve items of interest to users based on their interaction histories, have recently witnessed several key technological advancements, benefiting from the semantic representation space and model-data scaling. Nevertheless, practitioners and researchers have frequently encountered critical inconsistencies between simple offline evaluations and complex online results, and this gap still exists in the era of large models. In this work, we address several key factors that contribute to this inconsistency: 1) the \textit{large-scale continual learning challenge} that assumes a practical demand to maintain long-term model effectiveness under dynamic item pools and distributional shifts; 2) the \textit{combinatorial diversity challenge} that requires the generation strategy to solve the accuracy-diversity trade-off in both the finer token level and the holistic item level; and 3) the \textit{multi-task reward balancing challenge}, which is particularly critical for modern generative models that can accurately model the sequence distribution but are less controllable for the multi-task demands. To address these challenges and further pave the way for the development of more realistic recommendation solutions, we introduce KuaiRecV2, a deliberately constructed benchmark with industrial-level datasets from Kuaishou. Specifically, we provide a large-scale interaction dataset with million-scale multi-modal item information and long-term interaction records across 30 days, with a dynamic video candidate pool. Additionally, we provide a rigorous benchmark that evaluates retrieval accuracy, diversity, and multi-task performance in one rubric system, where an effective advancement occurs if and only if the new method improves all metrics. The code is available at https://github.com/cxli2333/KuaiRecV2
Research agents achieve increasingly strong benchmark scores, yet these scores do not necessarily translate into reliable delivery in ongoing research projects. Many research-agent benchmarks emphasize standalone tasks and relatively self-contained workflows in clean or curated workspaces. However, researchers ask agents to complete one step within an ongoing project, where requests depend on earlier session decisions and workspaces contain unfinished files, outdated versions, and failed attempts. We introduce ARE-bench to evaluate whether research agents advance ongoing projects while respecting prior decisions and existing workspace state, grounded in real session context and in-progress workspaces. ARE-bench includes 75 tasks built on agent sessions and full workspaces from recruited researchers' own projects, spanning seven research stages, 33 requirements, and 150 sub-requirements, with 1,173 binary checklist items in total. Each task is anchored at a real user request, preserves its requirements, and summarizes the earlier requests still in effect as background. The complete workspace is replayed to that boundary without cleanup, preserving artifacts from earlier turns. Each checklist is compiled from an intent-aligned rubric and credits any valid solution. Across seven frontier models, the strongest passes every checklist item on only 66.2% of tasks, and Design and Execution rank among the hardest stages for every model. Three models pass about 69% of tasks when only delivery contracts and general norms are checked, but just 28.4% to 40.0% once historical and material or workspace requirements are also checked. Evaluating delivery without these contextual requirements can therefore overestimate research agents and mask differences between them.
The escalating complexity of deep neural networks hinders the deployment of federated learning (FL) on resource-constrained devices, especially for multimedia applications such as on-device image classification and speech recognition. Parallel split learning (PSL) has emerged as a promising solution by offloading a substantial portion of the computational workload to the server through layer-wise model partitioning, making it particularly suitable for resource-limited visual and speech intelligence scenarios. However, the absence of client-side aggregation renders PSL sus ceptible to severe training divergence and potential convergence failure under heterogeneous data distributions. To address this challenge, we propose PSL-RGHA, a gradient-aligned PSL framework that employs reference gradient half-space alignment mechanism to mitigate training divergence among client devices. PSL-RGHA comprises two novel components: reference gradient progressive construction (RGPC) and gradient half-space alignment (GHA). Specifically, RGPC evaluates the directional consistency of client gradients and progressively synthesizes a robust reference gradient via Weiszfeld updates, effectively approximating the global descent direction. Then, GHA constrains client gradients within the reference half-space defined by RGPC to mitigate gradient conflicts and rectify local updates. Extensive experiments demonstrate that our PSL-RGHA framework outperforms existing baselines in various settings.
Generative driving planners can represent diverse ego futures, but a downstream scorer can choose only among sampled candidates; it cannot recover an absent maneuver. We present ForeseeDrive, which turns future scene evolution into a deployable interface for shaping candidate generation. Rather than reconstructing dense future states or scoring a fixed menu, ForeseeDrive derives query-indexed tokens from logged actor motion, occupancy evolution, route interactions, and TTC margins, and predicts the same token space from present context at deployment. The tokens condition trajectory geometry before candidates materialize. A zero-token-gated residual path and candidate-preservation loss limit unnecessary drift, while a TTC-margin guard targets brittle safe-to-unsafe boundary crossings. Under their respective benchmark protocols, ForeseeDrive reaches 89.2 PDMS on NAVSIM navtest, 0.41\,m average L2 and 0.05\% collision rate on nuScenes validation, and a 76.50 driving score on Bench2Drive. Controlled DiffusionDrive/NAVSIM diagnostics show an exact zero-token no-op, a small aligned-over-shuffled selected-PDM advantage under preservation, mixed oracle-best quality, and localized TTC-boundary failures. Together, the benchmark results and bounded mechanism tests support future-conditioned generation as a practical interface for anticipation. Code is included in the supplementary materials.
Hybrid models combine softmax attention with linear attention, which compresses history into fixed-size recurrent states to balance model quality and inference efficiency. However, linear attention has not pushed this compression to its limit: we find that the queries, keys, and values of linear layers concentrate in a stable, low-dimensional subspace, a phenomenon we call the linear attention sink, so each state is effectively low-rank, with a rank that varies across states. Yet existing serving systems keep these redundant states dense, reading and rewriting them in full at every decoding step, so their memory traffic grows with the batch size and dominates the decoding cost. Thus SinkState stores each recurrent state in an adaptive low-rank form throughout inference with buffered updates and a local SVD restricted to the top subspace. SinkState further consolidates the remaining components asynchronously on the CPU. On four hybrid models with Mamba-2 and Gated DeltaNet (GDN) layers, from 4B to 120B parameters, SinkState reduces the peak memory of recurrent states by up to 2.6x (1.9x on average) and speeds up decoding by up to 1.58x (1.25x on average) over Mamba-SSM and FLA, while maintaining accuracy.