Lei Huang, Chuan Qiu, Kuan-Jui Su, Anqi Liu, Yun Gong, Weiqiang Lin, Lindong Jiang, Chen Zhao 等 16 位作者
Genotype imputation enables dense variant coverage for genome-wide association and risk-prediction studies, yet conventional reference-panel methods remain limited by ancestry bias and reduced rare-variant accuracy. We present Genotype Bidirectional Encoder Representations from Transformers (GenoBERT), a transformer-based, reference-free framework that tokenizes phased genotypes and uses a self-attention mechanism to capture both short- and long-range linkage disequilibrium (LD) dependencies. Benchmarking on two independent datasets including the Louisiana Osteoporosis Study (LOS) and the 1000 Genomes Project (1KGP) across ancestry groups and multiple genotype missingness levels (5-50%) shows that GenoBERT achieves the highest overall accuracy compared to four baseline methods (Beagle5.4, SCDA, BiU-Net, and STICI). At practical sparsity levels (up to 25% missing), GenoBERT attains high overall imputation accuracy ($r^2 approx 0.98$) across datasets, and maintains robust performance ($r^2 > 0.90$) even at 50% missingness. Experimental results across different ancestries confirm consistent gains across datasets, with resilience to small sample sizes and weak LD. A 128-SNP (single-nucleotide polymorphism) context window (approximately 100 Kb) is validated through LD-decay analyses as sufficient to capture local correlation structures. By eliminating reference-panel dependence while preserving high accuracy, GenoBERT provides a scalable and robust solution for genotype imputation and a foundation for downstream genomic modeling.
Modeling asynchronous event sequences is crucial in numerous real-world applications such as healthcare monitoring, financial transaction analysis, and so on. Traditional temporal point processes, including Hawkes Processes, often fail to capture complex dependencies due to their parametric limitations. While neural approaches like RNNs and Transformers have improved flexibility, they struggle with computational inefficiency, and attention saturation. In this paper, we introduce the Mamba Hawkes Process (MHP), the first framework to integrate selective state space model (Mamba) with temporal point processes. MHP leverages time-varying state transitions and input-dependent gating to efficiently encode event history and capture long-term dependencies with linear complexity. Importantly, we provide theoretical guarantees showing that MHP generalizes both classical multi-exponential Hawkes processes and exponential-decay gated RNNs, underscoring its expressive power and theoretical soundness. To address the inherent constraints of pure state space models in handling heterogeneous event interactions, we further develop Adaptive Mamba Hawkes Process (A-MHP) that incorporates two novel mechanisms: a Time-Scaling Mechanism that adaptively weights time intervals based on event type and history, and a Dual-Channel State Transition that adaptively processes event content and temporal dynamics for more refined state updates. Extensive experiments on synthetic and realworld datasets demonstrate that MHP and A-MHP consistently outperform state-of-the-art baselines in event prediction tasks, particularly in long-sequence scenarios. Our work establishes a scalable and theoretically grounded paradigm for event sequence modeling, with practical implications for predictive maintenance, anomaly detection, and dynamic system analysis.
Junnan Nie, Zitian Fan, Jiachen Zhang, Junyi Lao, Likui Zhang, Chenghao Liu, Xiaoyang Lu, Yunbo Wang 等 17 位作者
Learning task progress from robot demonstrations provides a practical way to construct dense shaping rewards for robotic reinforcement learning. A common approach uses normalized demonstration time as progress labels, implicitly assuming monotonically increasing task progress. During policy exploration, however, actual task progress can stall or even regress. Such models may mistake regressions for progress, assigning positive shaping rewards to actions that cause progress loss. Real suboptimal and failed executions offer corrective experience, but assigning absolute progress values to their states is difficult. Our key observation is that stalls, regressions, and recoveries establish local relative progress relations even when absolute progress is unknown. We introduce Event2Reward, which uses normalized temporal labels to anchor the progress scale and these within-trajectory relations to constrain local changes, combining absolute and relative progress supervision. Its progress predictions serve as potentials for reward shaping. We curate an event-annotated dataset from approximately 100K raw real-robot execution records, covering successful, suboptimal, and failed executions, without requiring framewise absolute progress labels. Under the same training budgets, Event2Reward improves average policy success by 18.16 percentage points over a baseline using only sparse task rewards across 40 tasks in four LIBERO suites. On real robots, average success after 30 minutes of wall-clock training reaches 60.0% on three precise insertion tasks and 90.0% on three object manipulation tasks, exceeding the sparse-reward baseline under the same budget by 36.7 and 23.3 percentage points, respectively. Ablation studies further show that absolute progress supervision and relative progress relations are complementary, with joint supervision yielding better downstream policy learning.
Qiyang Li, Zhiyuan Zhou, Charles Xu, Sergey Levine
Modern robot learning systems feed on high-quality demonstration data, and their performance hinges on coverage. Without good coverage, small errors compound and the policy can quickly go into out-of-distribution states from which it cannot recover. Yet there is no principled way of collecting high-coverage data, and data collection often relies on heuristic instructions to human operators. Purely online reinforcement learning (RL) explores at the cost of safety and sample efficiency, while DAgger-style interventions require the policy to fail by chance before a human can correct it. In this paper, we ask instead whether we can modify how the robot behaves during data collection to collect more useful data. We propose Data Inoculation (DI), a shared-control framework in which a human provide closed-loop teleoperation commands while a residual policy perturbs these commands. The residual policy is trained online, on the growing dataset, with the same reward-maximizing objective later used for policy extraction, so its perturbations steer data collection toward the deviations a policy trained on the data would make. These perturbations expose the robot to a wider range of states, while the human's continuous corrections provide recovery demonstrations, "inoculating" the dataset against the learner's future mistakes while the human remains in control. On three challenging real-world robotic tasks, DI consistently improves or matches the success rate of policies trained with both behavioral cloning and offline RL, showing DI as an effective data collection strategy for improving downstream policy performance.
Within the open model ecosystem, AI model marketplaces enable non-AI experts to create and distribute derivative AI models. These platforms establish RAI approaches that creators are expected to follow to prevent negative downstream effects from model deployment, yet such governance approaches often rely on creators' intrinsic motivation and integrity. Little is known about how individual creators conceptualize their accountability for derivative models and how these conceptualizations shape their RAI practices throughout the development cycle. Through semi-structured interviews with 19 creators of derivative image-generation models on open model marketplaces, we identify two distinct accountability logics underlying creators' development practices: commons-based peer production and personal creative property. Guided by these logics, creators engage with platform RAI approaches in ways that diverge from their intended purposes: they strategically repurpose attribution tools for model visibility rather than provenance transparency, displace platform authority in favor of community-based governance, restrict model access to manage downstream accountability costs, and treat RAI-related work as undervalued labor to be minimized. We discuss how self-regulatory use of RAI tools, shaped by individuals' perceptions, produces shortcomings, and how open model marketplaces might mitigate these limitations by structurally supporting creators' engagement with RAI practices.
Lu Wang, Zhuoran Jin, Longxiang Wang, Junhong Chen, Yupu Hao, Yao Xu, Daojian Zeng, Yubo Chen 等 11 位作者
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has gradually shifted models from passive responders toward more proactive agents that can decide when to answer. However, existing proactive paradigms typically assume that the information required to answer a query is complete, leaving models to only wait or answer. In the real world, however, information is often incomplete due to uncertainty from either the video or the user. In proactive paradigms, such uncertainty can cause the model to wait forever or generate highly hallucinatory responses. We therefore argue that proactive interaction should be redefined with a third action: ask, allowing models to actively ask for missing information. To study when and what models should ask before answering, we introduce AskStream, the first multi-turn benchmark spanning video and user uncertainty for streaming video understanding, with four task categories and eight subtasks. It contains 438 videos with 2,714 manually annotated frame-level time windows across three types: wait, ask, and answer. Across both multiple-choice and open-ended settings, even the strongest model attains only 52.18% on our proposed Ask-F1 metric, highlighting substantial limitations in proactive information seeking under uncertainty.
Spectroscopic diagnostics provide rich information for characterizing plasma states in tokamak fusion experiments, while existing learning-based approaches are often designed for individual tasks and rely heavily on labeled data. In this work, we propose SpectralTF-MAE, a self-supervised spectral foundation model for tokamak plasma diagnostics. The model is pretrained on paired charge-exchange recombination spectroscopy (CXRS) and X-ray crystal spectroscopy (XCS) measurements through masked spectral reconstruction. To better capture diagnostically important spectral structures, we introduce a peak-aware masking strategy together with a peak-enhanced reconstruction objective, encouraging the model to focus on characteristic spectral regions. A shared Transformer encoder is employed to learn transferable representations across different diagnostic modalities. The pretrained model is further adapted to several downstream tasks, including plasma-parameter prediction, cross-diagnostic spectral generation, and spectral peak analysis. Experiments on EAST diagnostic data demonstrate that the proposed framework achieves competitive performance across different tasks and consistently benefits from self-supervised spectral pretraining. These results indicate the potential of SpectralTF-MAE as a general and transferable representation learning framework for plasma spectroscopic diagnostics.
A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evidence-grounded validity, and query-specific eligibility are distinct. We propose CALM, a conflict-aware lifecycle memory governance framework that decouples persistent memory preservation from query-time admission. CALM converts heterogeneous records into evidence-grounded memory cells, updates validity and lifecycle states using support, conflict, and dependency signals, and admits query-appropriate evidence through training-free or learned gating informed by temporal applicability. Across LongMemEval-S and LoCoMo with Qwen and GPT backbones, CALM outperforms state-of-the-art baselines, achieving the best overall accuracy. Compared with simple filtering and reranking, query-conditioned admission further improves evidence selection. Conflict-blocking and robustness analyses show CALM suppresses erroneous retrieved memories while retaining useful evidence. Historical-reconstruction experiments demonstrate that preserving superseded records supports accurate earlier-state reasoning without compromising current-state answers.
Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations reusable across sensing tasks. However, sparse detections and multipath effects make these observations unstable, challenging existing point cloud pretraining methods. We propose PT$^3$, a prototype-guided self-supervised pretraining framework for mmWave human point clouds. PT$^3$ represents local states in spatial regions as sparse compositions of shared prototypes and learns their temporal evolution through autoregressive prediction. Observation consistency further stabilizes representations under radar perturbations. After pretraining on unlabeled sequences from multiple sources, the same frozen encoder supports action classification, dense point generation, joint pose estimation, and future motion prediction on datasets not used for pretraining. Across these tasks, PT$^3$ outperforms the compared pretraining baselines and achieves competitive or superior performance to task-specific models.
Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline. While most research focuses on quantization and generation, the representation that bridges the two remains underexplored. Existing representation constructions mainly take two forms: either directly flattening the SID code embeddings into a sequence or merging them into a compact vector via external networks. While effective, they still expose two practical challenges: \textbf{1) Loss of item semantics:} Information lost by quantization or compression needs to be recovered during the representation stage. \textbf{2) Insufficient modeling of structured SID relations:} Intra-item code composition patterns and inter-item prefix-transition patterns are not explicitly preserved for representation and subsequent SID generation. To overcome these challenges, we propose \textbf{ComeIR}, a \textbf{\uline{Co}}nditional \textbf{\uline{me}}mory Enhanced \textbf{\uline{I}}tem \textbf{\uline{R}}epresentation framework that reconstructs SID code embeddings into item-aware inputs and preserves structured SID evidence for prediction. Item-guided Token Scoring estimates the contribution of each SID code using the item embedding employed by the quantizer. Dual-level Conditional Memory captures intra-item prefix composition and inter-item prefix transitions, while Memory Merge integrates these signals into each historical item representation. The Memory-restoring Prediction Head further conditions SID-level prediction on the generated prefix and historical transition evidence. Extensive experiments demonstrate the effectiveness and flexibility of ComeIR, and further reveal scalable gains from enlarging conditional memory.
Chumeng Liang, Linxuan Wang, Xinyu Peng, Huabin Liu, XiaoXu Guo, Yuxin Chen, Ge Liu, Guang Lin 等 10 位作者
Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass. Recent parallel drafters have achieved breakthrough performance in frontier production models, but their effectiveness deteriorates as the entropy of target distributions increases due to insufficient draft diversity. To overcome this bottleneck without sacrificing parallelism, we introduce UBTree, a parallel drafter that couples a Unigram proposer with a Bigram selector to construct drafting Trees. The unigram proposer is trained with the standard cross-entropy objective to generate candidate tokens independently for each position, while a lightweight bigram selector predicts transition scores between adjacent candidate pairs. Unlike the proposer, the selector is trained with a renormalized KL objective on high-temperature data. This tree-native training broadens the supervision beyond the greedy path, encouraging plausible alternative branches that improve the chance of accepting additional tokens during tree verification. Across seven standardized benchmarks with Qwen3-4B and Qwen3-8B, UBTree achieves an average speedup of $5.84$--$6.94\times$ over autoregressive decoding and outperforms DARTree in all 28 comparisons. Production-scale evaluation further demonstrates UBTree's advantage over frontier baselines such as DSpark.
Jiahui Li, Jiawei Sun, Zixiang Ren, Ming Liu, Jiamin Shi, Ruiteng Zhao, Zhiyang Liu, Liying Liu 等 10 位作者
Recent perception-free end-to-end (E2E) autonomous driving methods bypass explicit perception outputs by compressing dense image patch tokens into compact scene tokens for downstream trajectory generation and scoring. While these scene tokens form a compact visual bottleneck for the planner, they receive supervision solely from the planning objective, providing limited constraints on the encoded visual information. To address this limitation, we introduce Neural Token Reconstruction (NTR), a representation learning framework to directly constrain the compact scene-token bottleneck in perception-free driving. NTR introduces a self-distillation masked latent reconstruction objective that reconstructs masked patch-level latent features using only compact scene tokens as reconstruction memory. This forces reconstruction gradients to pass exclusively through the scene-token bottleneck, encouraging scene tokens to preserve richer and less redundant visual representations for planning. We further introduce semantic priors derived from foundation-model annotations as a weak semantic interface biasing reconstruction targets toward driving-related structures without introducing explicit perception heads. All auxiliary reconstruction components are removed at inference time, leaving the deployed planner unchanged. NTR achieves state-of-the-art performance on three public autonomous driving benchmarks, including 8.0461 RFS on Waymo E2E and 94.1 PDMS / 90.9 EPDMS on NavSim1&2. The learned scene tokens exhibit lower pairwise redundancy and higher effective rank, indicating that effective bottleneck supervision improves both compact visual representation learning and planning performance.
Minxing Chu, Anhang Li, Martins Atilla, Ruichen Qi, Mehdi Saligane
Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-rule-aware generators; however, writing such generators still takes expert effort. Large language models (LLMs) could now write generator code, and frontier models can even draw layout geometry from design intent. This raises a practical question: if a model can draw the layout itself, what does a generator framework still contribute, and is applying these models to a generator framework better than having them draw a layout from scratch? Through controlled experiments on gLayout in SKY130, we find that the main obstacle to drawing a layout directly is its time and token cost, and that the main advantage of a model building on a generator framework is reusability. Its verified primitives keep each model edit small enough to check, and its parameters allow a single edit to be evaluated across an entire family of layouts. Accordingly, a model is most effective when it develops the layout from the generator source of the family that the design intent belongs to, and tests each edit on the family members most likely to fail, so that one verified change improves every layout the generator produces. The results of these family tests can then serve as supervision for a local model, which learns edits that hold across the family at a fraction of the inference cost.
Ruopei Sun, Jianfeng Cai, Kangwen Zhao, Wengang Zhou, Houqiang Li
Context compaction lets long-horizon coding agents continue beyond their context windows, but can erase the state needed to finish a task. Prior evaluations measure efficiency, retained information, or end-to-end success, leaving the effect of a specific history replacement difficult to isolate. Compact-Bench pairs full-history and summary-only continuations from a shared repository state, and evaluates recurring details and successive production compactions. It covers 35 SWE-bench repairs, 146 agentic sessions, and 106 production chains. Across 14 summarizer backbones, stable damage ranges from 5-64% of 22 full-history successes: Claude Opus 4.8 preserves the most repairs, while DeepSeek-Flash damages the most. With Kimi-K3 as summarizer, the Kimi Code prompt preserves the most task continuations (19/22), whereas Claude Code retains the most recurring details (15.0%). LLM summaries retain at most 16.0% of recurring details, compared with 79.1% for mechanical extraction; production summaries retain 15.7% at the first boundary. Failures recur across methods: one repair is damaged by 13/14 backbones, and another by all 5 prompts. These results show that reliable compaction requires preserving the progress needed to complete a task, and that retaining relevant information alone does not ensure successful continuation. Code is available at https://github.com/cai-jianfeng/compact-bench and data is available at https://huggingface.co/datasets/caijanfeng/compact-bench.
Yuqi Qiu, Zuyao Xu, Lu Sun, Xiang Li, Fasheng Miao, Fubin Wu, Haixin Duan, Zheli Liu
The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source verification after delayed reading. How to organize these responsibilities so that cross domain communication does not depend on specific execution instances being continuously online is a key issue for building long term agent interaction infrastructure. We propose ATP (Agent Transfer Protocol), a cross organization agent communication protocol adopting a domain mediated architecture. In this architecture, administrative domains maintain stable addresses and receiving entries for logical agents. The domain servers of both parties continuously undertake cross domain transmission. The receiving domain verifies and saves messages for execution instances to read later. The sending domain signs the complete message envelope. This allows the receiving instance to independently reverify the domain source and content integrity after the original connection ends, provided the original verification public key is still trusted and obtainable. We implemented an ATP prototype and evaluated it through a controlled cross organization LLM agent workflow, mechanism checks and latency measurements. The workflow completed subsequent business processing after instances went offline or were replaced. The independent verifier successfully verified the domain source and content integrity of saved messages. Latency measurements further quantified the communication and processing overhead introduced by the continuous mediation of domain servers.
Junzhang Liu, Hao Yuan, Yiming Wu, Qi Zhang, Long Chen, Zhecan Wang
Effective video agents must learn not only how to answer, but also where to look next. Transferring this capability to smaller models is challenging because each observation serves two purposes: supporting an answer and guiding the search for further evidence. Textual descriptions may capture what is currently visible while omitting cues needed for subsequent acquisition. We introduce Latent Agentic Reasoning for Video Analysis (LARVA), a framework that distills multi-round video agents through jointly learned latent reasoning and visual observations. Rather than communicating through captions, an observer passes compact continuous representations to a reasoner that selects the next acquisition action or produces the final answer. Crucially, action and answer supervision propagate through this interface, training the observer to communicate information useful for downstream decisions. Observation reconstruction and reasoning-distribution alignment provide auxiliary supervision from textual teacher trajectories. Across five video-understanding benchmarks, LARVA achieves strong performance with 4B and 7B backbones. On VideoHolmes, Video-MME, and LVBench, the 7B model outperforms a textual CoT student trained on the same teacher trajectories by 5.1, 2.5, and 3.7 percentage points, respectively. These results highlight the value of jointly learning how agents represent evidence and act on it when distilling video-understanding capabilities.
Zhilong Zheng, Letian Tao, Yujie Yang, Wei Xiong, Kehua Sheng, Bo Zhang, Jingliang Duan, Keqiang Li 等 10 位作者
Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tuning methods, they adopted an overly restrictive Subspace Orthogonality condition. In this paper, we introduce a purely post-hoc and tuning-agnostic weight rectification framework that achieves Parameter Space Orthogonality, which is the necessary and sufficient condition for preserving historical performance to the first order. By projecting parameter updates into the JAcobian NUll Space (JANUS), our method significantly recovers compromised historical knowledge without interfering with the underlying fine-tuning process. To overcome the local validity of the Jacobian approximation, we further propose a Multi-step Adaptive Rectification mechanism that utilizes the JANUS shift to dynamically verify the valid trust region and adjust step sizes. Coupled with our proposed ghost projection, ghost orientation comparison, and sequence-level singular value decomposition compression techniques, JANUS also achieves great temporal and spatial efficiency. Experiments demonstrate that JANUS seamlessly integrates with various fine-tuning methods, significantly mitigating the stability-plasticity dilemma by recovering historical knowledge while preserving downstream task adaptation.
Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure.
Zhichun Jin, Zhicheng He, Hao Xu, Dongyang Li, Lin Wang, Hongliang Ren, Long Bai
Malocclusion skeletal grading is a fundamental task in orthodontics, critical for diagnosis and treatment planning. Traditionally, cone-beam computed tomography (CBCT) is used for visual measurement, and the reconstructed lateral cephalograms are handed over to expert dentists for diagnosis. However, manual review is time-consuming, labor-intensive, and subject to inter-operator variability. Therefore, an automatic CBCT-based system is needed for reliable malocclusion skeletal grading. In this case, we develop TeethGNN, a novel graph-based framework designed to combine CBCT image features with morphological information for accurate and efficient malocclusion grading. TeethGNN utilizes a decoupled learnable decoder to directly predict key morphological indicators from CBCT images, eliminating the need for manual measurements. These morphological features are then fused with image features using a graph neural network (GNN), which effectively models the relationships between the modalities. To further enhance robustness and calibration, we introduce a collaborative calibration strategy. This strategy combines multi-scale graph adversarial perturbation for explicit calibration and nonlinear topological graph calibration for implicit confidence adjustment. Extensive experiments and ablation studies on our collected clinical dataset demonstrate that our malocclusion measurement system achieves 77.08\% in accuracy and 89.61\% in AUC, outperforming the compared state-of-the-art methods. These results validate the effectiveness of graph-based multimodal fusion and collaborative calibration in improving malocclusion grading performance. Our system shows strong potential for advancing computer-aided orthodontic diagnosis, providing an accurate and reliable solution for vision-based clinical measurement and diagnosis.
Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical benchmarks and three model scales, STAPO consistently demonstrates superior entropy stability and achieves average accuracy improvements over baselines including GRPO, 20-Entropy, and JustRL under two widely-adopted evaluation settings.
Automatic judges offer inexpensive information about model outputs, but an evaluation team must decide how to turn that information into fewer human annotations. Scores can guide sampling, correct an estimate, or support adaptive acquisition, and these uses may capture overlapping gains. We compare their incremental value on fixed evaluation pools from three preference datasets, and 19 attributed-question-answering systems. Matched comparisons use the same scores, account for pilot labels and budget rules, and separate acquisition from estimation. Score stratification is a strong reference: after ten-bin stratification, the best fixed local linear correction offers only 1.00--5.27% further MSE reduction in the primary configurations. Unequal allocation offers larger gains in some pools, but can increase error when confident scores conceal variable human outcomes. Comparison on AttributedQA, shrinking learned quotas toward score-only quotas lowers pooled MSE for 17 of 19 systems relative to the score-only procedure, but ordinary pooled 95% intervals cover only 88.09--93.54%. The same shrinkage improves on the score-only reference in only one of eight preference configurations. Ranking experiments further show that lower individual MSE need not improve system selection. These findings support a simple starting procedure, proportional sampling within score strata followed by a stratified human mean, and identify what additional evidence is needed to justify correction or adaptation for the intended evaluation output.
ARC tasks can be formulated as visual transformation problems, where a model must infer a high-level transformation rule from a small set of demonstrations and apply it consistently across a grid. While dense Vision Transformers (ViTs) perform well in this setting, they entangle local visual state and global transformation logic within a shared token representation, which can hinder consistent reasoning. In this paper, we introduce RoSeViT, a role-separated Vision Transformer that explicitly decouples high-level instruction inference from visual workspace computation. RoSeViT uses controller tokens to aggregate transformation-level information and workspace tokens to represent the visual grid, with a structured attention pass in which nonlocal workspace interactions are routed through the controller. This design is motivated by our formal analysis showing that enforcing a shared instruction representation can reduce the effective complexity of visual transformation modeling. RoSeViT outperforms dense ViT baselines under the standard VARC training and evaluation protocol for ARC. In a controlled backbone replacement setting, it improves ARC-1 accuracy from 54.5 to 56.6, and with recurrent refinement reaches 58.8. When integrated into the full system, RoSeViT-Ensemble improves performance from 60.4 to 62.6 on ARC-1. These results demonstrate that explicitly separating instruction and workspace representations leads to more effective visual reasoning on ARC tasks. GitHub repository: https://github.com/lz7fd/RoSeViT.
Keepace. ai Team, Bowen Wu, Heng Wang, Jufeng Mi, Kang Liu, Kun Li, Ling Man, Long He 等 15 位作者
Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and rigorous evaluation benchmarks. Keepace.ai is a domain-specialized LLM built on Qwen3.5-27B through post-training, currently optimized for Chinese-language exercise guidance across three tasks: workout plan generation, sports-and-health knowledge QA, and personal sports data analysis. In internal rubric-based evaluations designed with domain experts, Keepace.ai outperforms its base model and larger general-purpose baselines, with the most pronounced improvements in exercise safety, boundary compliance, structured output completeness, and scientific accuracy. This report summarizes the current design, data pipeline, safety-first evaluation framework, and evaluation results of Keepace.ai.
Language models increasingly create 3D content through code, with practical workflows often relying on editing existing programs rather than regenerating them, for speed and precise control. Such edits require understanding what a program builds and foreseeing how a change reshapes it, yet prior benchmarks mostly evaluate generation or simple edits against a reference. In this paper, we introduce 3DCodeEdit, a benchmark of 2,592 instruction-guided editing tasks over 108 Blender programs that construct objects entirely in code. Its edits range from parameter to structural changes, style redesign, and scene composition, and are judged from renders against human-reviewed checklists. Across 17 models, the average success rate is only 37%, and even the strongest models complete fewer than 60% of structural and style edits. As models become more capable, their failures shift to geometric foresight, where the code runs but builds the wrong shape. We therefore study whether multi-turn feedback can compensate for this missing foresight. Feedback from a separate reviewer model that describes how the renders differ from the request helps most, more than maximum reasoning effort or an agent harness, and can let a 27B model surpass the single-shot rate of a 2.8T-parameter model.
Semi-dense local feature matching commonly aggregates contextual information before coarse-to-fine correspondence estimation. However, intra-image and inter-image aggregation serve different roles: the former should propagate spatial evidence within each image while retaining structured two-dimensional dependencies, whereas the latter should gather information from plausible corresponding regions while limiting noise from unrelated locations. We propose WovenAnchor Matcher (WAM), a semi-dense matching framework based on role-specialized context aggregation. WAM introduces two complementary operators. WovenMamba performs intra-image aggregation through horizontal-then-vertical state-space propagation, allowing vertical updates to operate on horizontally contextualized features and thereby encouraging a structured two-dimensional receptive-field bias. AnchorCrossAttention performs inter-image aggregation by using cross-attention to gather context from plausible corresponding regions across the image pair. It performs this exchange over local representative anchors that aggregate feature evidence within each window. On MegaDepth, WAM achieves 66.1 pose AUC@5$^\circ$, improving on the JamMa baseline by 2.0 AUC points under the same evaluation setup. Ablations show that removing or replacing either specialized component reduces accuracy, providing evidence that intra-image propagation and inter-image retrieval benefit from role-specific aggregation designs. Code and pretrained weights are available at https://github.com/mmaiLab/WovenAnchorMatcher.
Yuehang Li, Xiao Wang, Qiang Chen, Yangyi Fan, Bo Jiang, Yaowei Wang, Jin Tang
Industrial shampoo-bottle surface defect detection must operate across many stock keeping units (SKUs), where differences in bottle geometry, material, label layout, reflectance, and imaging conditions can substantially alter the appearance of the same defect. Existing industrial defect datasets rarely provide both instance-level defect annotations and product-variant identities, making it difficult to study SKU-aware detection under realistic manufacturing conditions. We introduce Bottle-SKU, a large-scale multi-SKU benchmark for shampoo bottle surface defect detection. Bottle-SKU contains 13,119 images, 20,419 instance-level bounding boxes, seven defect categories, and 48 bottle SKUs, enabling evaluation of both shared defect recognition and SKU-specific appearance variation. To address the challenge of SKU-specific appearance variation, we propose Prototype-Guided Dynamic Domain Modulation (ProDMM). ProDMM constructs a visual prototype for each SKU from training images and predicts a soft SKU distribution for each input. The resulting prototype-conditioned representation dynamically generates low-rank Query/Value modulation for the visual backbone and residual conditioning for defect-text-to-visual attention, while preserving the pretrained Grounding DINO detection pathway. The model is trained jointly with detection, SKU-domain classification, and modulation-regularization objectives. Experiments on Bottle-SKU and the public GC10-DET-SKU metallic surface defect dataset demonstrate the effectiveness of prototype-guided domain conditioning for industrial surface defect detection.
Zhefan Rao, Meng Chu, Xuan Billy Zhang, Jingfan Chen, Guohao Cai, Runyi Li, Shiyi Du, Xu Huang 等 92 位作者
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction requires separate evidence about action selection and state evolution. We introduce Dual Exam, which tests Agents under fixed environment response mechanisms and World Models under fixed action interventions across physical, digital, social, and scientific domains. The Agent track compares 10 configurations on 1,088 items in 15 reporting categories. The World Model track contains 400 cases across eight scenarios; 15 configurations have full coverage and one covers six scenarios. GPT 6 Astra leads the case-weighted Agent Index at 31.3, and GPT-Image-2 leads the full-coverage WM Overall at 21.7. These scores use different tasks and metrics and are not directly comparable. A 150-case pilot of one coupled pairing records zero task successes and motivates component-level diagnosis. Results reveal uneven task performance and failures to preserve task-relevant state. Their value for predicting coupled success or sustained reciprocal learning remains to be established.
Yang Li, Yike Wang, Di Wan, Chujun He, Zongsi Xu, Yitao Yu, Shuai Zhong, Minghao Pan 等 23 位作者
Simulating economic responses at society scale requires decision rules that respond to household circumstances and accounting rules that track their consequences. We introduce S$^2$-MAS, a multi-agent simulation framework with a resource of 500 million synthetic household personas. It combines trainable candidate-scoring policies, reusable financial scenarios and explicit state transitions. Trained with SFT + RLCD on 2.93 million examples, YN-mini-MLX achieves 74.55% accuracy and 38.37% question-macro F1 on held-out consumer financial-choice tasks, improving on the training-question majority baseline by 2.78 and 6.21 percentage points. A completed application evaluates 12 million distinct households in two purchase-funding conditions: 24 million one-shot choices feed 288 million monthly ledger states in 3 h 59 min on 14 GPUs. Jointly increasing purchase goals and approved limits produces heterogeneous consumption, cash and repayment paths, with much of the consumption variation arising from transitions between deferral and purchase. In a separate 1,060-household retrospective consumption experiment, standalone YN-master-9B has 3.42% lower annual MAE than the deterministic fully rational benchmark, alongside a 19.7% lower predicted population mean than observed. Information-timing tests show how year labels and later outcome information change decisions. Together, these experiments establish an executable alternative for studying heterogeneous household behavior with learned policies and explicit financial accounting.
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a framework for iterative pseudo-label refinement that integrates an instruction-tuned, audio-aware large language model (LLM) into the self-training loop. Unlike conventional text-based correctors, our approach conditions the LLM on both the ASR hypothesis and the source audio, allowing it to recover phonetically accurate transcripts even from severe recognition errors. These refined pseudo-labels serve as high-fidelity targets for fine-tuning the ASR model in an iterative cycle. Experimental results across diverse benchmarks demonstrate that ReHear effectively mitigates error propagation and improves over both supervised and pseudo-labeling baselines.