Inference
-
HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
2026-11-12 08:58:20Saehun Chun, Wonje Choi, Jinwoo Jang, Taeyoon Kwack, Honguk WooAbstract
Embodied agents make decisions by combining information from heterogeneous memory modules, including declarative memory for explicit knowledge, procedural memory for learned routines, and working memory for current observations. During interaction, the memory contents required for decision making change with the agent's state, goal, and task progress, while many contents remain shared across consecutive decisions. However, existing memory modules are typically accessed through separate interfaces, so each updated memory context is often processed as a new input to the foundation model. This prevents selective key-value (KV) cache reuse for unchanged memory contents and forces full KV cache recomputation even when much of the memory context remains valid. We introduce HeMeR, an inference framework that performs KV reconciliation between dynamically updated memory contexts and reusable KV states. HeMeR tracks declarative, procedural, and working memory contents across action decisions, preserves KV states for unchanged contents, and reconciles only the KV states affected by memory-content updates. This enables efficient and stable inference as memory contents evolve during interaction. We evaluate HeMeR on ALFWorld, Habitat, and real-world robotic deployments requiring coordinated use of heterogeneous memory contents. In the real-world setting, HeMeR achieves 83.20% task success and reduces per-step inference time from 2.94 to 1.87 seconds compared with MemRL, while preserving compatible KV states as task progress updates the memory context.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16487
PDF
-
Decoupled Asynchronous System for Humanoids : Latency-Agnostic Scaling of Vision-Language-Action Models for Humanoid Manipulation
2026-11-12 07:42:29Bingzhang Wang, Nathan Zhao, Jialeng Ni, Jiayin Zheng, Yin Zhang, Kehua Chen, Jian YaoAbstract
Vision-language-action (VLA) models pair a vision-language backbone with an action head, but in closed-loop control the backbone sits on the control-critical path: while it computes, the robot keeps moving, so each executed action is conditioned on an increasingly stale observation. A larger backbone therefore directly blocks reactivity, especially in humanoid dexterous manipulation. We present DASH, a Decoupled Asynchronous System for Humanoids that removes this coupling. DASH splits the policy into a slow vision-language model (System 2) and a fast flow-matching action head (System 1) that run as concurrent processes over the LCM communication protocol, so the control rate is set by the action head alone, independent of backbone size. The action head fuses stale semantics from a frozen backbone with fresh vision from its own ResNet encoder, desynchronized training exposes it to the staleness it meets at deployment, and an adaptive temporal aggregator aligns overlapping action chunks under variable inference latency. On an asynchronous RoboTwin benchmark that charges inference latency in simulated time, DASH holds 20 Hz control rate from 0.8B to 8B backbones while the synchronous rate falls from 9.7 to 4.1 Hz, with higher success at every size. On a real humanoid with dexterous hands, DASH achieves clearly higher pick-and-place success than the synchronous pipeline.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11854
PDF
-
SoScale: Second-Order Scale Search for FP4 Quantization
2026-11-12 07:36:46Pengxiang Zhao, Xing Li, Hui-Ling Zhen, Weizhe Lin, Xianzhi Yu, Zhenhua DongAbstract
Low-bit quantization reduces the memory footprint and inference cost of large language models (LLMs), yet accurate FP4 quantization remains challenging. Practical formats such as MXFP4, NVFP4, and HiF4 pair a 4-bit floating-point payload with block-wise or hierarchical scale codes, making accuracy highly sensitive to how each local distribution is scaled. Default maximum-absolute-value scaling preserves dynamic range, but can spend scarce FP4 levels on rarely occupied outlier regions and leave dense tensor values poorly resolved. Existing scale-search methods minimize local element-wise reconstruction error, optimizing tensor fidelity rather than layer-output fidelity. We propose SoScale, a second-order weight scale-code search method for hierarchical FP4 quantization. SoScale searches hardware-valid scale codes under a Hessian-aware layer reconstruction objective and couples this search with GPTQ-style error recovery, selecting scales by their impact on layer outputs. Across Qwen3 models, SoScale consistently reduces downstream quantization degradation under MXFP4, NVFP4, and HiF4.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16426
PDF
-
Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency
2026-11-12 07:25:46Sailendra Kolluru, Maheshkumar DuvvarapuAbstract
Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately. This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. The proposed framework uses prompt-driven small language models to make four independent capability decisions, allowing multiple capabilities to be selected per query. Qwen2.5 routers ranging from 1.5B to 14B parameters are compared across five prompting strategies, followed by an evaluation of capability-specific optimized configurations using a fixed GPT-OSS-120B downstream model on 127 questions. Under minimal prompting, increasing router capacity does not consistently improve classification performance. Prompt optimization narrows the capacity gap for reasoning and calculator routing, whereas RAG and web search retain larger benefits from higher capacity. Similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. The 14B router achieves a mean BERTScore F1 of 0.8408, compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7\% (8,837 to 2,764 tokens) and median downstream latency by 80.5\% (9.79 to 1.91 seconds). These savings exclude router overhead, which is measured separately in a different inference environment and increases with router capacity. The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. Consequently, router selection must consider error profiles and routing overhead alongside classification performance.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16414
PDF
-
Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression
2026-11-12 06:51:49Sikui Zhang, Haowei Liu, Ziyun Gan, Chunfeng Yuan, Guangze Gao, Nian Liu, Boyu Cai, Bo Li, Xiaolei Lv, Jun Gao, Bing Li, Weiming HuAbstract
As large language models (LLMs) advance toward increasingly long inputs, soft context compression offers a promising approach to efficient inference by converting long inputs into compact memory slots. Under limited memory budgets, effective context compression remains challenging because task-relevant evidence varies substantially across queries, ranging from localized evidence to multiple distant spans or information dispersed throughout the full document. Instead of compressing everything indiscriminately, we propose CoMem, a query-guided selective context compression framework that learns memory representations conditioned on both the document and the query. CoMem develops Contrastive Compressor Learning to achieve query-sensitive yet context-preserving memory representations. To inject a strong prior over query-dependent evidence distributions, we devise a same-context hard negative mining strategy by pairing a single document with multiple queries, requiring the compressor to selectively retain information according to each query's distinct evidence needs. To address the restricted information flow imposed by causal masking, we further enable bidirectional attention among memory slots. Experiments demonstrate that CoMem consistently outperforms existing context compression methods across compression ratios on question answering and RULER-NIAH benchmarks. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16384
PDF
-
Recursive State-Augmented Language Models: Persistent Latent-State Adaptation of Pretrained Language Models
2026-11-12 06:42:54Omer HaqAbstract
Language models rely on finite token contexts, limiting access to earlier interactions. We introduce Recursive State-Augmented Language Models (Recursive SALM), a framework in which a persistent latent state evolves with each observation and generates adaptations of a pretrained language model. A modular read-transition-write architecture separates observation encoding, latent dynamics, and predictor adaptation. We develop deterministic and stochastic formulations. The experiments evaluate only deterministic SALM with frozen GPT-2 small and exclude earlier evidence from its decoder context. On a four-turn hypothesis-inference task, latent-gated LoRA reaches 89.1% accuracy, comparable to 88.0% for a trained full-context LoRA baseline, with earlier evidence available solely through a 64-dimensional state. Zeroing or shuffling the state substantially reduces accuracy. In a two-turn task with codewords unseen in training, several interfaces improve candidate ranking over chance, but rarely generate the exact codeword under the evaluated training schedule. These experiments show that persistent latent-conditioned adaptation can support sequential inference when earlier evidence is absent from the decoder context.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16375
PDF
-
DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models
2026-11-12 06:04:08Yi-Hsin Hung, Fangfu Liu, Shao-Yuan Lo, Chu-Song ChenAbstract
Multimodal diffusion large language models (dLLMs) generate text through iterative masked denoising with bidirectional attention, offering a compelling alternative to autoregressive vision-language modeling. However, each denoising step requires a full forward pass over long multimodal sequences in which visual tokens dominate the sequence length, and a fixed step budget further compounds this quadratic per-step cost. Existing inference acceleration approaches for multimodal dLLMs characterize attention redundancy implicitly, motivating designs from isolated attention visualizations rather than from measurement. We close this gap with DRAMA, a training-free acceleration framework grounded in a systematic dissection of attention redundancy in multimodal dLLMs. By probing attention tensors along spatial and temporal axes, we reveal two persistent redundancy structures: (i) attention mass consistently concentrates on a sparse subset of visual tokens, and (ii) attention distributions rapidly stabilize across denoising steps after an initial formation phase. These findings motivate two complementary mechanisms: Spatial-Redundancy-Aware Visual Token Pruning (SVTP) and Sufficiency-Guided Adaptive Stopping (SGAS). Together, DRAMA achieves an average 18.67 times inference speedup across six vision-language benchmarks without training, architectural modification, or attention caching, while maintaining competitive accuracy. Our results establish a strong, measurement-grounded acceleration baseline for multimodal dLLM inference.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16345
PDF
-
From More to Better: Causal Inference and Digital Experimentation in the Age of AI
2026-11-12 05:56:52Winston Chou, M{\aa}rten Schultzberg, Lo-Hua Yuan, Wenjing Zheng, Avi Feller, David Holtz, Widad Machmouchi, Sven Schmit, Gagan Bhat, Simon Ejdemyr, Veronica Hannan, Amy Hartwig, Mahnaz Islam, Nathan Kallus, Jeremy Karp, Kyle Kretschman, Hannah Li, James McQueen, Evan Miller, Nicolas Stier, Sean TaylorAbstract
Artificial intelligence (AI) is quickly expanding the capacity of organizations to produce and analyze data. We argue that this expansion shifts the leverage of data scientists from performing individual analyses to assessing the credibility and importance of findings and determining when evidence generalizes across contexts. Drawing on a roundtable of academic researchers and industry practitioners, we examine three ways in which data scientists who work on causal inference and experimentation can help organizations turn more analytical capacity into better decisions: preserving and accumulating the learning value of experimentation beyond individual tests; choosing and combining experimental, observational, and synthetic evidence; and ensuring evaluation keeps pace with AI as its capabilities and uses evolve. In each area, we distinguish established practice from open questions. We conclude with implications for the training and practice of data science and for organizations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16335
PDF
-
SMIC: Shared Multiscale Input-Reference Conditioning across Transformer Layers for Natural Language Inference
2026-11-12 04:15:47Xin Zhang, Victor S. ShengAbstract
Natural Language Inference models can be sensitive to localized lexical changes. We introduce Shared Multiscale Input-Reference Conditioning (SMIC), which constructs a single input-dependent multiscale reference and reuses it across Transformer layers. Each layer applies its own multiscale transformation to the shared reference and injects the resulting conditioning feature before the attention update. We instantiate SMIC in a token--context Transformer (TCT) and conduct from-scratch comparisons against decoder-based and Multi-Layer Perceptron (MLP) baselines across all three ANLI rounds. TCT-SMIC attains the highest observed ten-seed mean accuracy on all three ANLI rounds. The ablations further support the contribution of SMIC. We evaluate a real-valued Llama-style plug-in and extend deletion/insertion diagnostics to pretrained ModernBERT encoder and Llama decoder models with and without SMIC. Across the evaluated perturbation protocols, TCT-SMIC exhibits comparatively low pooled-attention redistribution and smaller signed accuracy changes. We further establish a finite-sample bound on average subset-mass redistribution in terms of the mean Jensen--Shannon divergence between the restricted and renormalized attention distributions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16270
PDF
-
Rectified Looped Transformer
2026-11-12 04:07:40Musheng Li, Jiawei Zhang, Ziyuan Liu, Yuantao GuAbstract
Looped Transformers increase effective depth by repeatedly applying a shared block, offering a parameter-efficient approach to language modeling. However, most existing works directly reuse each loop's output as the next's input, which can lead to hidden-state scale growth and perturbation amplification as recurrence deepens. We propose Rectified Looped Transformer (RLT), which redesigns feedback between loops using an interpolation schedule inspired by flow-based modeling. At each loop, RLT forms the next input by linearly interpolating between the current state and its prediction. Such interpolation distributes state changes across loops, encouraging a smoother trajectory from the initial input to the final output. Theoretical analysis proves that, under appropriate assumptions, RLT keeps state magnitudes uniformly bounded across loops and reduces the worst-case perturbation amplification. We evaluate RLT on language modeling corpora and downstream benchmarks. At matched training and inference depths, RLT consistently achieves lower perplexity than a standard looped Transformer, while exhibiting greater robustness to input perturbations and variance in inference depth. Consistent with the theoretical results, latent trajectory analysis shows that RLT maintains more stable hidden-state norms across loops, which also facilitates extrapolation-based decoding strategies. Notably, RLT achieves these gains without requiring additional trainable parameters or extra recurrent block evaluations, thus providing a simple yet more stable feedback mechanism for looped Transformers.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16265
PDF
-
Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning
2026-11-12 04:06:48Chao Chen, Shanshan Lin, Dongsheng Hong, Sibo Ju, Wenjie Yang, Sihong Xie, Xiangwen LiaoAbstract
Large language models (LLMs) can generate fluent claims that are unsupported by a given source document, motivating accurate and efficient document-grounded factuality detection. Existing LLM-based evaluators often require repeated inference and incur high computational cost, whereas compact factuality detectors are efficient at inference time but commonly rely on large labeled or synthetically generated corpora. We propose CPIL (Cross-Paraphrastic Invariance Learning), a two-stage Siamese framework that converts a small labeled set into relational supervision without acquiring additional factuality labels. CPIL constructs positive pairs from distinct label-preserving paraphrastic views of the same document-claim instance and negative pairs from opposite-label examples associated with the same source document. It further introduces quantile-aware semi-hard negative mining, which derives a boundary from the positive-pair similarity distribution and balances informative negatives with broader coverage. In the two-stage training procedure, Stage 1 learns an encoder from these task-aware pairs, and Stage 2 jointly fine-tunes the encoder and a linear classification head for binary factuality prediction. At inference time, CPIL requires no paraphrase generation, pair construction, or Siamese comparison and uses only one encoder-classifier forward pass. On the 11-task LLM-AggreFact benchmark, CPIL-2% and CPIL-3% achieve macro-F1 scores of 81.04 and 81.60 while using only 2-3% of the FactCG-released labeled pool. Both settings outperform all compared compact detectors and two vanilla LLM references. Ablations and sensitivity analyses support the contributions of task-aware pair construction, dynamic negative mining, and multi-pivot paraphrasing.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16264
PDF
-
JudgeMix: Judge-Guided Mixed-Rollout Data Synthesis for LLM Agents
2026-11-12 02:03:23Cheng-Yu Hsieh, Ting-Yao Hu, Sanjoy Chowdhury, Oncel Tuzel, Raviteja VemulapalliAbstract
Supervised fine-tuning (SFT) on expert trajectories is a standard paradigm for training LLM agents. However, it suffers from a well-known training-inference distribution mismatch, calling for target-aware data synthesis strategies that ground the training data in the target model's native state distribution. To bridge this gap, emerging approaches incorporate the expert either to guide mixed rollouts alongside the target model, or to provide dense step-wise supervision. Nonetheless, existing methods apply expert assistance blind to the target model's inherent behavior: they either disrupt the rollout using sub-optimal random intervention heuristics, or they enforce indiscriminate uniform supervision that unnecessarily overwrites the model's already-correct actions. We introduce JudgeMix, a judge-guided data synthesis framework that dynamically interleaves the target model and expert based on step-wise semantic evaluations. JudgeMix queries expert guidance precisely when the target model struggles, ensuring high trajectory success rates while keeping the state distribution aligned with the target model. It additionally uses the judge evaluation to reweight expert supervision on different steps, preserving model's inherent valid behavior while correcting its errors. On two agentic tool-use benchmarks, AppWorld and AutomationBench, JudgeMix demonstrates consistent superior performance to existing methods, with improvements up to 10 pass@1 points.
Abstract (translated)
URL
https://arxiv.org/abs/2611.16174
PDF
-
Program Learning with Verifiable Rewards: Distilling Expert Traces into Programs
2026-11-12 00:38:11Vishvesh Bhat, Muhammad Ahmed Mohsin, Asad AaliAbstract
Small language models struggle with tool-use tasks that require following multi-step procedures. Whether these failures reflect limited capability or missing procedural knowledge remains unclear. We introduce Program Learning with Verifiable Rewards (PLVR), which distils expert traces into reusable programs without updating model weights. Frontier models turn recurring operations in the traces into typed primitives and rules, and search assembles them using reference actions and training-task checks. A small frozen model executes the primitives, with deterministic verifiers checking their outputs. The resulting program guides a student's reasoning or checks its proposed actions. We evaluate the same program across students on $\tau^2$-Bench Retail and Telecom and LiveMCPBench, using synthetic training tasks and unseen benchmark test tasks. On Telecom, PLVR raises an 8B model's success rate from 43.0% to 91.2%, while larger students reach up to 94.4%, compared with 57.9% for the best baseline. On Retail and LiveMCPBench, PLVR is competitive with the best baselines, although tool search remains more dependent on the student model. These results support program learning as a way to transfer expert procedures across frozen models, trading additional inference computation for more reliable tool use.
Abstract (translated)
URL
https://arxiv.org/abs/2610.19148
PDF
-
Large Payments Model
2026-11-11 18:30:35Natraj Raman, Abhenandhan Manoharan, Vishwasreddy Thuniki, Dhvani Kansara, Anirudh Som, Hassan Firouzi, Kostis Gourgoulias, Laukik Hoshing, Sudhir Kanala, Austin Reiter, Ebby Abdul, Shantanu Chandra, Ryan Schmiedl, Zack Anderson, Sumitra GaneshAbstract
Payment applications such as fraud detection, authorization prediction, and payment optimization draw on overlapping transaction information. This motivates a reusable payments intelligence layer that shares learned representations and predictive signals, rather than developing predictive models independently for each task. Realizing this shared capability requires handling heterogeneous transaction fields, high-cardinality identifiers, lifecycle-dependent attributes, long histories, and rare outcomes while meeting latency and cost constraints. We present Large Payments Model (LPM), a domain-specific foundation model designed for operational use and trained from scratch on large-scale structured transaction data to learn reusable representations for payment prediction tasks. LPM employs field-specific encodings and lifecycle-aware self-supervision in two complementary architectures: the Independent variant uses hybrid masking and supports efficient per-transaction inference, while the Sequence variant incorporates entity-linked histories through compact latent representations for richer temporal context. Optional distillation enables resource-constrained deployment. We pretrain LPM on up to 400 billion tokens and study scaling, downstream performance, and representation reuse. LPM improves over strong task-specific baselines across multiple prediction tasks in Merchant and Treasury Services, demonstrating applicability in distinct payment domains. Its representations also facilitate adaptation to a target not observed during pretraining through compact task-specific components. Together with production deployment, these results position LPM as a practical basis for reusable payments intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15814
PDF
-
Learning-Based Interpolation of Detector Gaps in Photon-Counting X-ray Imaging
2026-11-11 15:31:56Johannes B. Thalhammer, Patrick Ilg, Tina Dorosti, Sebastian Peterhansl, Theresa Hiu, Daniel Frey, Zijin Huang, Florian Schaff, Daniela Pfeiffer, Franz PfeifferAbstract
Image detectors assembled from tiled modules have physical gaps in the field of view that must be filled before downstream processing such as phase retrieval or tomographic reconstruction. Unlike natural-image inpainting, detector-gap interpolation must leave all other pixels unmodified and preserve the intensity statistics of the filled region, since even a small shift in mean intensity can cause ring artifacts after reconstruction. We adapted two generative models, a Wasserstein GAN with gradient penalty (WGAN-GP) and a conditional Pix2Pix model, to this task. We implemented a masking strategy that restricts all changes to the gap pixels and loss terms that constrain the mean intensity and the intensity distribution of the filled region. Both models were trained on nanoCT projections with simulated gaps and compared with linear interpolation, Navier--Stokes inpainting, and the deep image-inpainting network MADF, quantitatively on simulated gaps and visually on real detector gaps. WGAN-GP and Pix2Pix achieved the best perceptual similarity (LPIPS) and histogram distance and, apart from linear interpolation, the shortest inference time. Pix2Pix required about five times fewer training GPU-hours than WGAN-GP. Ablation studies showed that masking the network output contributes by far the most to plausible inpainting results. Applied to sinograms, Pix2Pix produced the most natural gap filling but improved the reconstruction only slightly compared with linear interpolation. The source code and the weights of the final Pix2Pix model are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15614
PDF
-
LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends
Abstract
Visual agents need to coordinate reasoning and action while their environment evolves during inference. We introduce LOLPlay, a benchmark in native League of Legends with 36 champion-specific tasks spanning resource management, combat, cooperation, and objectives. Agents interact through screenshots and mouse-keyboard actions; automated initialization and 82 executable subgoal checks distinguish partial progress from completion. Across 324 task evaluations of three models at three reasoning-effort settings, GPT-6 Astra achieves the highest task success rate of 25.0% at low and medium effort, and the highest subgoal success rate of 40.3% at medium effort. However, high effort improves neither metric over low effort for any model. For Astra, longer requests leave fewer interaction rounds, suggesting a cost to additional reasoning in real-time control. Trajectories reveal incomplete subgoal composition and actions executing after the observed scene changes, motivating agents that combine visual reasoning with timely action.
Abstract (translated)
URL
https://arxiv.org/abs/2611.03685
PDF
-
MemCredit: From Relevance to Utility for Decision-Time Memory in Long-Horizon Web Agents
2026-11-11 15:17:38Quanjiang Guo, Sijie Wang, Qianyang Zhu, Ben Zhang, Jinchuan Zhang, Ke Yan, Zhao KangAbstract
Large language model (LLM) agents increasingly operate over long Web interaction histories, making memory management critical for reliable and efficient decision making. Existing methods primarily optimize storage, retrieval, or compression, but the memories most semantically relevant to the current state are not necessarily those that most improve the agent's action. We introduce MemCredit, a decision-centric memory framework that shifts memory selection from semantic relevance to decision utility. MemCredit estimates the state-, reference-context-, and policy-conditional marginal contribution of individual memories through controlled counterfactual interventions, and distills these intervention-derived credits into a lightweight utility estimator. At inference time, semantic relevance is used only for high-recall candidate generation, while predicted utility arbitrates which memories are retained under a fixed token budget, without modifying the underlying agent policy or requiring additional environment interaction. We evaluate MemCredit on ALFWorld and WebShop against representative memory baselines. On ALFWorld, MemCredit achieves 86.57 SR@50 under a 500-token historical-memory budget, compared with 65.67% for BM25 retrieval. Counterfactual analysis further shows that memory utility is sparse, strongly state dependent, and poorly captured by semantic relevance. These results suggest that decision utility provides a more effective principle than relevance alone for long-horizon agent memory management.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15600
PDF
-
Small Heads, Strong Decisions: A Controlled Study of Typed-Decision Models
Abstract
In September 2026, TypeSafe announced Jev as the first model in its System One category: unstructured state goes in, and typed, calibrated decisions that software can use directly come out. Jev's architecture and training data are unpublished, but many open typed-decision models have followed, including Nimble, the Decision 1.0--3.0 family and Clef. They answer structured questions about a piece of text, such as a yes/no check, a choice among labelled options or a graded score, by reading the text with a language model and scoring the options with a small readout. Each pairs a different readout with a different backbone, training mix and recipe, so it is unclear which design choices matter. We re-implement five readouts and train all of them under one protocol: the same backbone, the same 15 public English training sources, the same recipe with a per-head learning-rate sweep, and the same seed. Our experiments demonstrate that: The complexity of the head does not affect accuracy: on Qwen3-0.6B every readout reaches 81.3--82.0\% in-domain accuracy, and a 0.5M-parameter cosine head, which scores each option by its cosine similarity to the question, matches the 27M-parameter joint schema head adapted from Clef in-domain at half its inference time. Reading all of a text's questions from one prompt also matches one prompt per question in accuracy, with 1.6 times faster inference and 2.1--2.5 times faster training on one H100. The backbone's size matters more than either choice: moving from Qwen3-0.6B to Qwen3-4B adds 4 points in-domain and 11 points on held-out sources, while the base, instruct and thinking checkpoints of the same model tie. We recommend spending effort on the backbone and keeping the head minimal.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15592
PDF
-
Marginal-Preserving Coupled Diffusion Composition for Long-Horizon Planning
2026-11-11 15:07:26Hengrui Zhang, Qiyu Wang, Yuhu Cheng, Brooks Paige, Xuesong WangAbstract
Compositional diffusion planners extend short-horizon trajectory models to long-horizon goal-conditioned planning by generating and stitching multiple local trajectory chunks. However, in multimodal environments, local plausibility is not sufficient for global consistency: independently initialized chunks may denoise toward incompatible overlap modes, producing plans that are individually feasible but incoherent after stitching. Existing remedies typically add search, guidance, pruning, or graph-based structure at inference time, increasing computational cost or relying on task-specific machinery. We instead investigate graph-structured dependence among chunk-wise initial diffusion noises as a lightweight coordination mechanism for compositional trajectory planning. We propose \textbf{M}arginal-Preserving \textbf{C}oupled \textbf{D}iffusion \textbf{C}omposition (MCDC), a training-free inference method for pretrained compositional diffusion planners. Instead of sampling chunk noises independently, MCDC constructs coupled Gaussian initializations whose per-chunk marginals remain exactly standard Gaussian, as required by the pretrained denoiser, while neighboring chunks receive positively correlated noise components. This preserves the standard-Gaussian initialization marginal of each chunk while biasing adjacent chunks toward compatible overlap-mode choices. We prove exact marginal preservation and show, under a simple multimodal overlap model, that positive coupling increases the probability of compatible mode selection. On OGBench long-horizon stitch tasks, MCDC consistently improves over independent compositional diffusion sampling while retaining nearly the same inference time, and achieves a favorable success--cost trade-off compared with search-based composition methods.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15585
PDF
-
WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration
2026-11-11 13:28:18Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser, Muzammil BehzadAbstract
Underwater image restoration remains challenging because color distortion, scattering, and detail loss affect low- and high-frequency image components differently. Recent diffusion-based methods have shown strong restoration quality, but often rely on multi-stage pipelines and costly iterative refinement. We present WaveFlow-UIE, a single-pipeline wavelet-domain flow model that directly learns to transform degraded underwater wavelet representations into clean ones. Our method applies a discrete wavelet transform, estimates lightweight physics-inspired degradation cues including transmission and ambient light, and conditions a velocity network trained with flow matching in wavelet space. The training objective combines flow-matching, frequency-weighted reconstruction, perceptual, color-consistency, and physics-consistency losses. Across UIEB, LSUI, UFO-120, and EUVP, WaveFlow-UIE achieves a strong quality-efficiency tradeoff, with especially competitive results on perceptual metrics. Relative to a strong wavelet-based diffusion baseline, the proposed model substantially reduces inference cost while maintaining or improving restoration quality on several paired benchmarks. We show that reducing the inference process from five flow steps to a single step preserves nearly all of the restoration quality while providing an additional speedup of about $4\times$ on UIEB at $256\times256$ resolution. This single-step result suggests that a single-pass wavelet-domain model is an effective alternative to heavier diffusion-style refinement.
Abstract (translated)
URL
https://arxiv.org/abs/2611.15457
PDF
