跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 01:46 — 2026-11-19 01:46(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2611.00403

MXCode: Vector Quantization for MX-Native Inference at Scale

Gaurav Kolhe, Cansu Demirkiran, Shubhi Tyagi, Sulaiman Sadiq, Boyao Wang, Richard Wang, Maximiliana Behnke, Shreyas Labhsetwar 等 11 位作者

原文摘要

Memory capacity and bandwidth are major bottlenecks in LLM inference, motivating weight compression beyond conventional 4-bit quantization. Vector quantization (VQ) enables approximately 2-bit weight storage but often relies on codebooks incompatible with native FP4 computation. We introduce MXCode (MX-Native Codebook Quantization), a framework bridging ultra-low-bit VQ compression with MicroXcaling (MX)-native FP4 computation. MXCode proposes three strategies: PostScale, which quantizes learned codebooks to MXFP4; PreScale, which extracts MX scales before codebook learning; and PreScale+, which further compresses these scales using VQ. These strategies explore tradeoffs among quantization quality, scale overhead, and codebook granularity. All reconstruct MX-native W4A4 operands without materializing intermediate high-precision weights. We evaluate MXCode on Qwen3 (235B), DeepSeek-R1 (671B), and GLM-5.2 (753B) using the Microsoft MX Emulation Library. MXCode achieves approximately 2 bits per weight with competitive, workload-dependent model quality. On GB300 hardware, experiments with Qwen3 (235B) show approximately 50% lower model-load memory than Native FP4 while maintaining near-Native-FP4 serving throughput. Under memory-constrained prefix reuse, P90 TTFT improves by up to 94.5%. These results demonstrate software-based reconstruction on existing FP4 hardware and inform the development of future MX-native inference systems.

cs.LG

版本更新 · v2arXiv:2611.07654

English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models

Tomas Rasymas, Povilas Kvedaras

原文摘要

Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant. Studies of high-resource languages largely find that English calibration transfers well to other languages. We test this for Lithuanian: we pruned four MoE models with REAP, removing 25% or 50% of the experts with English, Lithuanian or mixed calibration, and evaluated both languages on reading comprehension, translation and language modelling. English calibration does not transfer to Lithuanian: at 25% pruning, English comprehension fell by a median of 1.7 points but Lithuanian by 21.4. The transfer is asymmetric. Lithuanian calibration removed most of the Lithuanian loss and never significantly hurt English comprehension, which was on average 2.5 points better than under English calibration; only English language modeling got slightly worse. Routing suggests why: in the last layers, Lithuanian sends 55-72% of its expert selections to just eight experts, against 19-39% for English, and English calibration removes some of these experts. Compressed models should be calibrated, and evaluated, in every language they must serve.

cs.CL · cs.LG

版本更新 · v2arXiv:2610.16776

Game-Creation-Agents: Autonomous Game Production

Xiangxin Zhou, Jiaqi Tang, Ke Ma, Wenhao Yang, Jiarui Yao, Boye Niu, Haiyang Guo, Yifei Zhao 等 17 位作者

原文摘要

Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples mechanics and scene contracts to grounded visual references. It then projects that document into a runtime scaffold, machine-readable contracts, and deterministic tests. Eight specialized agents next carry out production: scenes are implemented serially, assets are produced in parallel, and one reduced manifest joins the two branches into a single build. Build-linked real-UI checks and a code-blind critic then verify that build and decide whether the game may ship. Each blocker returns to the agent that owns the affected artifact for a bounded repair, and the game is released once all the gates pass. We evaluate finished games separately, through their rendered interfaces alone, over prompt-matched tasks run under a common protocol. GCA achieves stronger requirement satisfaction, core mechanics, content depth, and functional visuals than a comparable open pipeline. In a side-by-side human study, raters also score GCA's games higher on every dimension and prefer them overall.

cs.AI · cs.MA

版本更新 · v2arXiv:2609.31351

Progressive Memory Transformer: Memory-Aware Attention for Time-Series

Tord Sture Stangeland, Andreas Köhler, Steffen Mæland, Adín Ramírez Rivera

原文摘要

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level contrastive losses and limited temporal neighborhood supervision, but do not explicitly exploit the structural hierarchy. We propose a learning framework that explicitly enforces a structural hierarchy across three scales independently: a local objective for token alignment, a mid-range objective for window-level motifs, and a global objective for sequence-level agreement. Realizing this framework requires the backbone to expose a representation at each scale; we introduce \textbf{Progressive Memory Transformer} (PMT), which augments a transformer with writable, window-aligned memory that exposes the mid-range scale alongside the token and sequence-level representations conventional transformers already provide. Across eight UCR/UEA/UCI classification benchmarks, a cue-retention probe, and forecasting benchmarks, PMT learns representations that probe well at the global, mid-range, and local scales---strong low-label classification (1--5\% labels), competitive forecasting performance across multiple horizons, and quantitative and qualitative evidence that memory states capture mid-range motifs.

cs.LG

版本更新 · v3arXiv:2609.33158

FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs

David Restrepo, Chenwei Wu, Luis Filipe Nakayama, Miguel L. Martins, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante

原文摘要

Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance reported on a single dataset does not capture how models behave under dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging, where robustness, calibration, and fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-Dataset Understanding under Shift), a cross-dataset benchmark evaluating retinal fundus models across vision-only encoder models (VM), vision-language dual-encoder models (VLM), and multimodal large language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public datasets spanning diverse geographies, acquisition conditions, and label protocols. The benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted via LoRA fine-tuning. Results show no model family consistently dominates across tasks and datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual-encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external datasets, particularly in calibration. FOCUS provides a practical framework and public benchmark to assess generalization, reliability, and robustness beyond single-dataset leaderboards.

cs.CV · cs.AI

版本更新 · v2arXiv:2605.05413

From History to State: Constant-Context Skill Learning for LLM Agents

Haoyang Xie, Xinyuan Wang, Yancheng Wang, Puda Zhao, Feng Ju

原文摘要

Large language model (LLM) agents are increasingly used to operate browsers, files, code and tools, making personal assistants a natural deployment target. Yet personal agents face a privacy-cost-capability tension: cloud models execute multi-step workflows well but expose sensitive intermediate context to external APIs, while local models preserve privacy but remain less reliable. Both settings also pay repeatedly for long skill prompts and growing histories. We propose constant-context skill learning, a context-to-weights framework for recurring agent workflows: reusable procedures are learned in lightweight task-family modules, while inference conditions only on the current observation and a compact state block. A deterministic tracker renders this state block from task progress and supplies aligned subgoal rewards, so each module can be trained with step-level SFT and refined through online RL. Across ALFWorld, WebShop, and SciWorld, our agents achieve strong performance across Qwen3-4B, Qwen3-8B, Qwen3-14B, and Llama-3.1-8B. With Qwen3-8B, SFT+RL reaches 89.6% unseen success on ALFWorld, 76.8% success on WebShop, and 66.4% unseen success on SciWorld. They match or exceed strong published agent-training results while reducing prompt tokens per turn by 2-7x relative to controlled ReAct prompting baselines, showing that procedural context can be moved from prompts into weights. Code is available at https://github.com/haoyangxie/constant-context-skill-learning.

cs.AI

版本更新 · v3arXiv:2605.07483

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization

Leonel Aguilar, Jan Nagler, Christoph Hoelscher, Nino Antulov-Fantulin

原文摘要

Deep neural networks can learn salient features from an in-distribution (ID) training window without identifying the data-generating structure needed for out-of-distribution (OOD) generalization. Understanding this limitation requires examining the identifiability of the data-generating process (DGP). From a single training window, the DGP that yields the correct OOD extrapolation is not identifiable: infinitely many DGPs are observationally equivalent within a fixed tolerance on that window yet diverge arbitrarily beyond it, and no ID criterion alone can reliably distinguish them. A structural commitment---the feature map, label map, and model class $(\varphi, ψ, \mathcal{M})$---specifies the assumed DGP and governs OOD generalization while leaving ID performance essentially unchanged. When architecture, pretraining, data augmentation, input formats, or domain knowledge implicitly supply the correct commitment, the model generalizes beyond the training window. When it cannot infer OOD-relevant structure from ID evidence, it fails to generalize. When the commitment is correct {\em and} identifiable, OOD error vanishes. We demonstrate this mechanism in models trained from scratch and in foundation models across four natural-science settings (chemistry, physics, biology, and histopathology), as well as in a positional-encoding study spanning Transformer, Mamba, and S4D architectures. Finally, a controlled study shows that correct features are necessary but not sufficient for OOD generalization.

cs.LG · cs.AI

版本更新 · v3arXiv:2510.13879

Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production

Alexandre Galashov, Matt Jones, Rosemary Ke, Yuan Cao, Vaishnavh Nagarajan, Michael C. Mozer

原文摘要

Within the landscape of inference-time scaling methods for foundation models, a width-based approach to scaling--which involves the insertion of <pause> tokens in the input stream to delay model responses--offers a unique advantage by increasing model expressivity while remaining highly parallelizable at both training and inference. The existing literature on training models to utilize <pause> tokens relies on the standard cross-entropy objective in which the model output is read out and evaluated only at the final step of a pause sequence. This approach provides no mechanism for the model to regulate its own processing or to signal readiness to respond, treating the additional compute steps as a barrier to skip over rather than a resource to be used adaptively. We propose a supervised loss, Catch Your Breath (CYB), framed as a sequential-decision problem, that trains a model to dynamically and autonomously scale the number of compute steps used for each input token. The model indicates the need for additional compute steps by emitting a special <don't know> output, delaying its response via a pause. The model can abstain multiple times to obtain longer delays. Our experiments demonstrate that when <pause> tokens are included in the input stream, pretraining or fine-tuning with CYB significantly outperforms standard cross-entropy, reducing perplexity and enhancing downstream accuracy with no additional computational or memory cost.

cs.CL · cs.AI

版本更新 · v4arXiv:2601.02950

Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning

Xuan Yang, Furong Jia, Roy Xie, Xi Xiong, Hengwei Bian, Jian Li, Monica Agrawal

原文摘要

Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning patterns and consistency constraints. We introduce Batch-of-Thought (BoT), a training-free method that processes related queries jointly to enable cross-instance learning. By performing comparative analysis across queries, BoT identifies high-quality reasoning templates, detects errors through consistency checks, and amortizes computational costs. We instantiate BoT within a multi-agent reflection architecture (BoT-R), where a Reflector performs joint evaluation to unlock mutual information gain unavailable in isolated processing. Experiments across three model families and six benchmarks demonstrate that BoT-R consistently improves accuracy and confidence calibration while reducing inference costs by up to 61%. Our theoretical and experimental analysis reveals when and why batch-aware reasoning benefits LLM systems. Our code is available at https://github.com/xuanyang19/BoT.

cs.AI

版本更新 · v3arXiv:2601.09920

SyncTwin: Fast Digital Twin Construction and Synchronization for Safe Robotic Manipulation

Ruopeng Huang, Boyu Yang, Wenlong Gui, Jeremy Morgan, Erdem Biyik, Jiachen Li

原文摘要

Accurate and safe robotic manipulation under dynamic and visually occluded conditions remains a core challenge in real-world deployment. We introduce SyncTwin, a novel digital twin framework that unifies fast 3D scene reconstruction and real-to-sim synchronization for robust and safety-aware robotic manipulation in such environments. In the offline stage, we employ VGGT to rapidly reconstruct object-level 3D assets from RGB images, forming a reusable geometry library. During execution, SyncTwin continuously synchronizes the digital twin by tracking real-world object states and uses stored assets to complete partially observed geometry. The synchronized twin enables motion planners to compute collision-aware robot trajectories in simulation, with execution on the real robot closing the real-to-sim-to-real loop. Experiments in dynamic and occluded scenes show that SyncTwin improves manipulation performance and motion safety, demonstrating the effectiveness of digital twin synchronization for real-world robotic execution.

cs.RO

版本更新 · v8arXiv:2608.05543

omni-macos: On-Device Omni-Modal Search on Apple Silicon

Han Xiao

原文摘要

We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs on the Mac that already holds the files, so the files, the queries and the vectors stay on that machine. A background indexer and an interactive search box share the device. Each distinct chunk is embedded and stored once, and every file becomes searchable from a small first share of its content. Indexer work is split into smaller units while the user types, and one memory setting reaches every allocator found to draw on unified memory. Once the index is large, queries scan a one-bit replica of it, rescore a shortlist exactly and rank every modality in one list on a common score scale. The engine can also leave the GPU entirely, with the encoder on the Neural Engine and search on the CPU. We measure omni-macos on five Macs spanning an eightfold range of accelerator width and a thirty-twofold range of memory, and its ranking on a labeled multilingual and multimodal testbed. omni-macos is open source under Apache 2.0 at https://github.com/hanxiao/omni-macos.

cs.IR

版本更新 · v2arXiv:2611.06956

Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning

Tianming Sha, Junnan Li, Siqi Zhao

原文摘要

Deep search and long-horizon reasoning unfold as branching trajectories that pursue parallel sub-queries, abandon dead-end detours, and cross-check sibling findings. Yet modern serving engines, harnesses, and RL trainers execute episodes as flat, append-only sequences: stretching a context window leaves failed detours that dilute attention, in-place edits break KV caching and recurrent states, and all-layer cache splicing overwrites hybrid recurrent working memory and triggers hijacking. We introduce Octopus, a co-designed serving runtime, memory manager, and RL framework executing episodes as a GPU-resident DAG over radix cursors (89.6% KV hit rate). Agents coordinate via five primitives: fork shares parent KV prefixes in $O(1)$ with isolated 32K budgets, rewind restores recurrent checkpoints, read_thread mounts sibling KV pages in zero copy, and wait and done synchronize results. Octopus splices sibling KV pages only into full-attention layers under monotonic position offsets while recurrent layers skip mounted spans, retaining 92.2% of full-text answer information and cutting hijacking $21\times$ ($57.9\% \to 2.7\%$) with zero new KV pages. During RL, our packed DAG kernel and DAG-GRPO objective deduplicate shared prefixes via loss masks while keeping mounted KV edges differentiable, cutting rollout-training KL divergence $32\times$ and routing reader gradients into producer KV projections. Trained on Qwen3.5-4B with binary rewards, Octopus self-organizes a commander-worker hierarchy and latent KV mesh, lifting BrowseComp-Plus accuracy under BM25 from 26.0% (32K ReAct) and 32.1% (143K GRPO) to 49.6% (+17.5 pts; 51.2% on OpenResearcher), surpassing 9B context-editing RL (42.5%), matching o3 (49.3%), and outperforming dense-retrieval agents up to $250\times$ larger: Tongyi-DeepResearch (44.5%), DeepSeek-R1 (16.4%), Kimi-K2 (35.4%), GPT-4.1 (36.4%), and Claude 4 Opus (36.8%).

cs.LG · cs.CL

版本更新 · v3arXiv:2605.01507

MILD: Mediator Agentic System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

Jiyao Wang, Yunbiao Wang, Yubo Jiao, Xiao Yang, Dengbo He, Sasan Jafarnejad, Luis Miranda-Moreno, Raphael Frank 等 9 位作者

原文摘要

Prior studies report that partial driving automation can increase the cognitive demands on human drivers. This effect largely arises from human drivers' lack of transparent insight into the vehicle's intentions and decision logic, as well as from automated systems' limited awareness of the driver's dynamic state and preferences. This bidirectional misalignment undermines shared situational awareness and exacerbates coordination failures in human-vehicle interaction. To address these limitations, we argue for a paradigm shift that elevates the human role from passive supervisor to active manager. We introduce the Mediator-in-the-Loop-Driving system, based on an agentic system architecture to facilitate synergistic human-vehicle collaboration. MILD integrates a perception agent for joint in-cabin and out-of-cabin understanding with a lightweight strategy agent that generates compliant and explainable action suggestions. To ensure these strategies are strictly aligned with safety regulations and human values, we develop Evidence- and Constraint-weighted Policy Optimization. ECPO leverages automatic validators to steer the agent toward behaviors that are not only accurate but also structurally complete, substantiated by evidence, and less prone to constraint violations. Furthermore, a retrieval-augmented generation module dynamically incorporates constraints from traffic regulations, speed recommendations, and driver preferences into the decision loop. Experiments across three open datasets demonstrate that MILD consistently outperforms baselines in both perception accuracy and strategy quality under auditable offline metrics, and yields higher human-rated policy adequacy, comfort, and explanation than baselines.

cs.AI

版本更新 · v2arXiv:2610.31471

Ask About the Right Moment: Training-Free Object Identity Reasoning for Video-Language Models

Di Yang, Xiaochang Li, Muyang Liu, Yufei Wang, Yanhai Xiong

原文摘要

Many questions about a video concern one physical object. Where does the ball end up after the cups are shuffled? Which card is the queen? How often was the mug covered? Open video-language models (Video-LMs) recognise such objects in single frames but do not keep them apart over time. On shuffled shell games, open models from eight families stay near chance, and so do published tool agents. We separate semantic identity binding from temporal identity maintenance. Binding should happen at a moment when the evidence for the object is visible, and maintenance should be left to a tracker. Track, Then Bind implements this principle without training. A promptable video tracker follows every candidate object and draws it with a track number. A frozen vision-language model (VLM) answers one question about the identifying evidence, which binds the target to a track. The answer is then derived from a text description of the tracks. With Qwen3-VL-32B, the agent solves both VET-Bench tasks, where a fine-tuned trajectory model reaches 92% and 90%. On real cup games from the Perception Test, it raises accuracy from 35.5% to 52.3%. Without retuning, the same configuration also solves VET-Bench with Gemma 4 and GPT-5.5. Its track-derived visibility timelines add 8.8-17.9 points on TOC-Bench for open models. GPT-6.1 already answers 92.5% of the real cup games directly but 71.0% through our pipeline, while our timelines still raise its TOC-Bench accuracy from 52.5% to 57.7%. The benefit of external tracking thus depends on the underlying model and the task.

cs.CV

版本更新 · v4arXiv:2511.03724

Beyond Reasoning: RL-Policy Guided LLM Inference for Efficient Strategy in Liar's Poker

Richard Dewey, Janos Botyanszki, Ciamac C. Moallemi, Andrew T. Zheng

原文摘要

AI researchers have long focused on poker-like games as a testbed for environments characterized by multi-player dynamics, imperfect information, and reasoning under uncertainty. While recent breakthroughs have matched elite human play at no-limit Texas hold'em, the multi-player dynamics are subdued: most hands converge quickly with only two players engaged through multiple rounds of bidding. In this paper, we present Solly, the first AI agent to achieve elite human play in reduced-format Liar's Poker, a game characterized by extensive multi-player engagement. We trained Solly using self-play with a model-free, actor-critic, deep reinforcement learning algorithm. Solly played at an elite human level as measured by win rate (won over 50% of hands) and equity (money won) in heads-up and multi-player Liar's Poker. Solly also outperformed large language models (LLMs), including those with reasoning abilities, on the same metrics. Solly developed novel bidding strategies, randomized play effectively, and was not easily exploitable by world-class human players. In one extension, when Solly's policies were provided to LLMs as a domain-specific guide for inference, LLM performance improved and token costs decreased. This result suggests that low-cost RL agents can be used to boost LLM efficiency and reasoning capabilities.

cs.AI · cs.MA

版本更新 · v2arXiv:2611.06348

Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes

Hendrik Mehrtens, Florian Buettner, Oliver Stegle

原文摘要

Temporal point processes (TPPs) are the canonical model class for event sequences in continuous time, with applications ranging from seismology to electronic health records. Recent benchmarks report that neural TPPs substantially outperform their classical counterparts, such as Hawkes processes. However, these comparisons set flexible neural models against Hawkes processes in their most restricted forms and covered only a narrow range of domains. We revisit this comparison under autoregressive next-event prediction, evaluating Poisson and Hawkes processes of increasing flexibility against neural TPPs on five established benchmarks and two large-scale medical tasks derived from UK Biobank disease histories and MIMIC-IV ICU records. First, once Hawkes processes are equipped with flexible, learnable baselines and kernels, the previously reported gap to neural TPPs largely closes. Second, neural TPPs are likewise limited by their intensity parametrization: a Transformer with a spline-based intensity head outperforms previous intensity-based neural TPPs and matches or exceeds the intensity-free model. Decomposing the log-likelihood into time and type terms shows that this gain lies almost entirely in modeling when events occur (log p(t)) rather than which type occurs (log p(d|t)). Third, only on MIMIC-IV do neural TPPs retain an advantage in predicting event types, underscoring the value of complex datasets for evaluating TPPs. We release TorchPP, an open-source PyTorch framework with unified implementations of classical and neural TPPs.

cs.LG · stat.ML

版本更新 · v2arXiv:2611.07847

Computation, not weight access: large language models as auditors of clinical prediction networks

Zhiyu Liu, Xinyu Yang

原文摘要

Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files alone. Public demonstrations, however, mixed reading raw weights with running code. We separated these conditions in internally pre-specified simulation experiments. Tanh networks of 105 to 38,401 weights were trained on simulated cohorts of patients with subarachnoid haemorrhage, each with a planted relationship or none, and one network was trained on labels that under-recorded deaths in a subgroup. GPT-6 Astra and four other GPT models answered single prompts under a default or an explicit system instruction, either with the weights in the prompt and no tools, or with a calculation-only tool that exposed the weights (white box) or only the network's predictions (black box). Without tools, Astra recovered planted relationships in 353-weight networks but became unreliable at 3,457 weights, and under the default instruction it declined 17 of 21 audit and repair tasks as unidentifiable; the explicit instruction removed these refusals. With the tool, it recovered the planted relationship in all 39 runs on networks of up to 38,401 weights, raised no false alarm in 21 runs on null networks, and found the biased subgroup in 6 of 6 runs. Black-box access performed as well as white-box access, and other GPT-6 models read as accurately. A well-designed script matched the comparator models on the audit and the best LLM repair. For auditing these networks, what mattered was computation and elicitation, not access to the weights.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.07328

DC-SQEM: Medial Mesh Extraction by Dual Contouring with Spherical Quadric Error Metric

Bingchuan Li, Ruilong Liu, Tianhao Hu, Congyi Zhang, Ningna Wang, Junfeng Yao, Xiaohu Guo

原文摘要

The medial axis, as a compact representation, describes not only the boundary but also the interior of the shape, and has been widely used in analyzing and simplifying shapes. However, approximating feature-preserving medial axis from unstructured data, such as oriented point clouds, remains challenging due to the lack of explicit connectivity and the presence of noise in the source. We propose DC-SQEM, a dual-contouring-based framework that computes medial meshes (an explicit representation of the medial axis) directly from oriented point clouds without relying on watertight manifold surfaces or volumetric structures. With the help of an adaptive octree, our method fits local medial spheres for each cell based on the Spherical Quadric Error Metric (SQEM). We address several long-standing robustness issues in dual-contouring and mesh extraction, including out-of-cell solutions, unstable feature classification, and redundant topological connections. To this end, we introduce virtual nodes, a feature-downgrading strategy, and a geometry-driven topology-aware cleanup procedure, enabling robust SQEM-based medial dual contouring with clean mesh outputs. Unlike prior point-cloud-based methods that produce either only 1D skeletal structures or incomplete medial features, our method preserves sharp geometric features from the input and reconstructs a complete medial structure, including sheets, curves, seams, and junctions. Compared to restricted-power-diagram-based approaches, our algorithm can handle point clouds as input, without having a strong requirement on water-tightness or manifoldness.

cs.GR

版本更新 · v2arXiv:2606.30509

Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics

Mark Rhee, Jamie Simon, Dhruva Karkada

原文摘要

Matrix factorization (i.e., problems of the form $\min_{\mathbf{P},\mathbf{Q}} \|\mathbf{M}^\star - \mathbf{P}^\top\mathbf{Q}\|_\mathrm{F}^2$) is a minimal learning problem that exhibits both nonlinear parameter dynamics and representation learning. In this setting, we study how parameter trajectories under the Muon optimizer differ from those of gradient descent. We identify three main dynamical differences: (1) Muon avoids the slow saddle-to-saddle dynamics of GD from small initialization. Muon instead learns all the top singular vectors of $\mathbf{M}^\star$ at the same rate, and they saturate in order of increasing (rather than decreasing) singular value. (2) Muon does not diverge even when the learning rate exceeds the critical threshold set by the local loss sharpness. This frees the learning rate from the condition number of the problem, enabling rapid convergence via exponential learning rate annealing. (3) Once the weights are aligned with each other and the target, Muon flow conserves the matrix quantity $\sqrt{\mathbf{P}^\top \mathbf{P}}-\sqrt{\mathbf{Q}^\top \mathbf{Q}}$, while gradient flow is known to conserve the matrix $\mathbf{P}^\top\mathbf{P} - \mathbf{Q}^\top\mathbf{Q}$. Despite having distinct conserved quantities, both optimizers find the so-called balanced solution from vanishing initialization. When training from small random initialization, the weights spontaneously align early in training. We derive the alignment rates in simple settings and show that they predict the empirical alignment rates in general. Finally, we exploit structural properties of Muon to construct a learning rate schedule that achieves near-perfect alignment in only two optimization steps.

cs.LG

版本更新 · v2arXiv:2605.06086

LARGO: Low-Rank Hypernetwork for Handling Missing Modalities

Niels Vyncke, Pooya Ashtari, Aleksandra Pižurica

原文摘要

Addressing missing modalities is an important challenge in multimodal image analysis and often relies on complex architectures that do not transfer easily to different datasets without architectural modifications or hyperparameter tuning. While most existing methods tackle this problem in feature space by engineering representations that are robust to missing inputs, we instead operate in weight space. We propose LARGO, a hypernetwork that compresses the $2^N-1$ dedicated missing-modality models into a single network by modelling the convolutional weights using the Canonical Polyadic (CP) tensor decomposition. Extensive experimental validation on BraTS 2018 (4 modalities, 15 scenarios) and ISLES 2022 (3 modalities, 7 scenarios) shows that our method ranks first in 47 out of 52 configurations, achieving average Dice improvements of +0.68$\%$ and +2.53$\%$ over state-of-the-art baselines (mmFormer, M$^{3}$AE, ShaSpec, SimMLM). A proof-of-concept experiment on avMNIST suggests that LARGO may extend beyond medical imaging to heterogeneous non-medical modalities. Code is available at https://github.com/nielsvyncke/LARGO.

cs.CV

版本更新 · v2arXiv:2604.14886

Cooperate to Compete: Strategic Data Generation and Incentivization Framework for Coopetitive Cross-Silo Federated Learning

Thanh Linh Nguyen, Nguyen Van Huynh, Quoc-Viet Pham

原文摘要

In data-sensitive domains such as finance, cross-silo federated learning (CFL) allows organizations to collaboratively train AI models without sharing raw data. However, many practical CFL deployments are coopetitive, where organizations cooperate during model training while competing in downstream markets. In such settings, training contributions can improve the global model yet inadvertently strengthen rivals, eroding one's competitive advantage. This dilemma is amplified by non-IID data, which leads to asymmetric learning gains and undermines sustained participation. While existing work reward organizations based on marginal training contributions, they fail to account for the implicit costs of strengthening competitors. In this paper, we introduce CoCoGen+, a coopetition-compatible data generation and incentivization framework that jointly models data heterogeneity and inter-organizational competition while endogenizing GenAI-based synthetic data generation as a strategic decision. Specifically, CoCoGen+ formulates each training round as a weighted potential game, where organizations strategically decide how much data to generate by balancing learning gains against computational costs and utility losses caused by competition. We establish the existence and uniqueness of the continuous Nash equilibrium under the adopted model and develop a provably convergent scalar bisection algorithm. We further analyze how bilateral payoff redistribution modifies residual competition and data-generation incentives, and empirically evaluate the social welfare and individual utilities of the resulting allocations. Experiments on FMNIST, CIFAR-10, and CIFAR-100 validate the feasibility of CoCoGen+. The results show how heterogeneity, competition intensity, and incentives shape organizational strategies and social welfare, while CoCoGen+ achieves higher social welfare than competition-aware baselines.

cs.AI · cs.DC · cs.GT

版本更新 · v3arXiv:2601.02322

Environment-Adaptive Covariate Selection: Learning When to Use Spurious Correlations for Out-of-Distribution Prediction

Shuozhi Zuo, Yixin Wang

原文摘要

A common approach to out-of-distribution prediction restricts models to causal or invariant covariates to avoid spurious associations that may change across environments. Despite its theoretical appeal, this strategy can underperform empirical risk minimization when only a subset of the causal parents of the outcome is observed. In such settings, non-causal covariates can serve as proxies for unobserved causal parents and improve prediction when the proxy relationship is stable, but they can hurt when shifts disrupt that relationship. Thus, the optimal covariate set can depend on the specific shift encountered. Because different shifts can leave distinct signatures in the covariate distribution, we propose an environment-adaptive covariate selection algorithm that chooses which covariates to use in each environment based on summaries of its unlabeled covariates. The summaries may be hand-crafted or learned from multi-environment data, and prior causal knowledge can be incorporated as constraints. We give sufficient conditions under which such summaries are informative in linear causal models, and explain when adapting only the covariate set is preferable to letting every coefficient vary with the environment. In simulations and two applications, adapting the covariate set improves prediction over static baselines, including causal and invariant covariate selection.

stat.ME · cs.LG

版本更新 · v2arXiv:2603.04399

SimpliHuMoN:简化人体运动预测

SimpliHuMoN: Simplifying Human Motion Prediction

Aadya Agrawal, Alexander Schwing

AI 速读 基于摘要

作者提出一种简洁的端到端 Transformer 模型,用统一的架构同时处理姿态预测、轨迹预测及二者联合的人体运动预测。

cs.CV · cs.LG

查看原文摘要

Human motion prediction combines the tasks of trajectory forecasting and human pose prediction. For each of the two tasks, specialized models have been developed. Combining these models for holistic human motion prediction is non-trivial, and recent methods have struggled to compete on established benchmarks for individual tasks. To address this, we propose a simple yet effective transformer-based model for human motion prediction. The model employs a stack of self-attention modules to effectively capture both spatial dependencies within a pose and temporal relationships across a motion sequence. This simple, streamlined, end-to-end model is sufficiently versatile to handle pose-only, trajectory-only, and combined prediction tasks without task-specific modifications. We demonstrate that this approach achieves state-of-the-art results across all tasks through extensive experiments on a wide range of benchmark datasets, including Human3.6M, AMASS, ETH-UCY, and 3DPW.

版本更新 · v2arXiv:2605.10707

ObjView-Bench:重新审视以物体为中心的视角规划中的难度与部署问题

ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning

Sicong Pan, Hao Hu, Xuying Huang, Benno Wingender, Maren Bennewitz

AI 速读 基于摘要

提出 ObjView-Bench 评估框架,将物体复杂度、规划难度与预算/可达性约束解耦,并揭示这些因素如何改变视角规划方法的排名与失效模式。

cs.RO

查看原文摘要

Object-centric view planning is a core component of active geometric 3D reconstruction in robotics, yet existing evaluations often conflate object complexity, planning difficulty, budget assumptions, and physical reachability constraints. As a result, conclusions drawn from idealized view-planning evaluations may not reliably predict performance under realistic reconstruction settings. We introduce ObjView-Bench, an evaluation framework for rethinking difficulty and deployment in object-centric view planning. First, we disentangle three quantities underlying view-planning evaluation: omnidirectional self-occlusion as an object-side attribute, observation saturation difficulty, and protocol-dependent planning difficulty defined through a set-cover formulation. This separation supports controlled dataset construction, analysis of slow-saturation objects, and a case study showing that planning difficulty-aware sampling can improve learned view planners. Second, we design deployment-oriented evaluation protocols that reveal how budget regimes and reachable-view constraints alter method behavior. Across classical, learned, and hybrid planners, ObjView-Bench shows that difficulty, budget, and reachability constraints substantially change method rankings and failure modes. Project page: https://objview-bench.github.io/

版本更新 · v2arXiv:2602.16696

Simple models outperform single-cell foundation models on downstream benchmarks

Huan Souza, Pankaj Mehta

原文摘要

Single-cell RNA sequencing (scRNA-seq) data exhibit strong and reproducible statistical structure. This has motivated the development of large-scale foundation models, such as TranscriptFormer, that use transformer-based architectures to learn a generative model for gene expression by embedding genes into a latent vector space. These embeddings have been used to obtain state-of-the-art (SOTA) performance on downstream tasks such as cell-type classification, disease-state prediction, and cross-species learning. Here, we ask whether similar performance can be achieved without utilizing computationally intensive deep learning-based representations. Using simple, interpretable pipelines that rely on careful normalization and linear methods, we obtain SOTA or near SOTA performance across multiple benchmarks commonly used to evaluate single-cell foundation models, including outperforming foundation models on out-of-distribution tasks involving novel cell types and organisms absent from the training data. Our findings highlight the need for rigorous benchmarking and suggest that the biology of cell identity can be captured by simple linear representations of single cell gene expression data.

q-bio.GN · cs.LG · q-bio.QM

版本更新 · v3arXiv:2505.01353

可微分非线性模型预测控制

Differentiable Nonlinear Model Predictive Control

Jonathan Frey, Katrin Baumgärtner, Gianluca Frison, Dirk Reinhardt, Jasper Hoffmann, Leonard Fichtner, Sebastien Gros, Moritz Diehl

AI 速读 基于摘要

提出在内点法平滑最优性条件下用隐函数定理计算一般非线性规划的解灵敏度,并以序列障碍二次规划(SBQP)统一推广 SQP,配套 acados 开源实现。

math.OC · cs.AI · cs.LG

查看原文摘要

The efficient computation of parametric solution sensitivities is a key challenge in the integration of learning-enhanced methods with nonlinear model predictive control, as their availability is crucial for many learning algorithms. This paper discusses the computation of solution sensitivities of general nonlinear programs using the implicit function theorem and smoothed optimality conditions treated in interior-point methods (IPM). We introduce sequential barrier quadratic programming (SBQP), which generalizes SQP with an IPM quadratic programming (QP) solver by allowing the barrier parameter to approach a prescribed nonnegative target value, recovering classical SQP when this target is zero. Previous works are limited to convex or unconstrained formulations, or lack an implementation for efficient sensitivity evaluation. The publication is accompanied by an efficient open-source implementation within the `acados` framework, providing both forward and adjoint sensitivities for general optimal control problems, achieving speedups exceeding 3x over the state-of-the-art solvers `mpc.pytorch` and `cvxpygen`.

版本更新 · v3arXiv:2608.14753

AuditLock:面向合成表格数据发布的预指定验证审计

AuditLock: Pre-Specified Verification Audits for Synthetic Tabular Data Releases

Jeffery Opoku, David Banahene

AI 速读 基于摘要

提出一种在打开受保护审计样本前预先锁定用途、候选、分析与容差的“锁定审计”协议,并报告两轮预指定确认性审计的证据记录。

cs.CR · stat.ME

查看原文摘要

A statistical office with a synthetic version of a protected file must decide whether it may be released for a stated purpose. We study the locked audit, a pre-specified and simultaneous form of the verification servers used in official statistics. Before a protected audit sample is opened, the custodian fixes the use, the candidates, the analyses, a tolerance for each and the schedule. The audit then reports simultaneous finite-sample bounds on paired loss gaps, and a declared negative control must fail. We correct an anytime-valid sequence that an earlier release had implemented with a variance penalty four times too small. Two confirmatory rounds were pre-specified in a hash-locked local ledger and publicly timestamped only after the audits. The control and ideal-generator outcomes were near-certain by design. A Gaussian copula certified in every cell, but only inside the rounding step of the tolerance rule. A second transparent candidate certified once, against a written prediction. Learned models, at library defaults and 4,000 training rows, certified in one of 18 fits in round 1 and in none of 12 tables in round 2. The paper is a protocol and an evidence record, not a claim that any generator is private or deployable.

版本更新 · v3arXiv:2510.03086

链式2-FWL GNN用于组合图对齐

Chaining 2-FWL GNNs for Combinatorial Graph Alignment

Marc Lelarge

AI 速读 基于摘要

作者提出将多个Folklore型(2-FWL)GNN串联训练,以离散排序反馈逐步改进图对齐,并在稀疏随机图、相关正则图和真实基准上报告了优于FAQ及既有GNN方法的结果。

cs.LG

查看原文摘要

For the combinatorial graph alignment problem (GAP), finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs, the classical Frank-Wolfe heuristic FAQ remains a strong baseline once it is properly initialized, while existing GNN approaches struggle in the purely structural setting. We introduce a chaining procedure: a sequence of Folklore-type (2-FWL) GNNs in which each network is trained with cross-entropy after decoding the previous network's similarity matrix and ranking nodes by their current alignment quality. This non-differentiable ranking step injects discrete combinatorial feedback at every stage; at inference, we iterate the final network and keep the candidate with highest observed nce. On sparse Erdos-Renyi graphs at noise level 0.25, chained FGNNs used to initialize FAQ reach 85% accuracy versus 13% for FAQ initialized from the convex relaxation, and essentially 0% for prior GNN methods. On correlated regular graphs, where MPNNs with constant features produce identical node embeddings (1-WL fails to refine) and FAQ's convex initialization is degenerate, chaining is the only method among those we evaluate, including Gromov-Wasserstein solvers, that recovers a non-trivial alignment. On three real-world benchmarks (yeast PPI, coauthorship, and road networks), recent comparisons underestimate FAQ by initializing it from a uniform doubly stochastic matrix; initialized from the convex relaxation it already surpasses prior reported numbers, and dataset-specific chained FGNNs further improve on this strengthened baseline. Code and pretrained chains available at: https://github.com/mlelarge/chaining-gnn-graph-alignment.

版本更新 · v3arXiv:2609.03080

Exemplar:数秒内完成的小样本生物医学分割

Exemplar: Few-Shot Biomedical Segmentation That Fits in Seconds

Michal Průšek, Adam Novozámský, Filip Šroubek

AI 速读 基于摘要

Exemplar 用闭式解拟合线性分割读出层,结合冻结的 DINOv3 特征与经典滤波响应,在数秒内完成小样本生物医学分割,并随新增标注精确更新。

cs.CV

查看原文摘要

Segmenting a new microscopy dataset usually means training a deep network on its annotations, and training again for every added image. Exemplar solves a segmentation readout in closed form and updates it exactly with each new mask in seconds, as accurately as networks trained for minutes. The updated readout is identical to a fit from all masks at once. Its linear readout combines frozen DINOv3 features, read at a magnification chosen from the masks, with classical filter responses at native resolution. Its regularisation and its pixel weighting are chosen exactly by leaving out one annotated image at a time, so none is set aside for validation. On ten biomedical datasets from cells to vessels and filaments, Exemplar is more accurate than every few-shot method that only applies a pretrained model, and on average than nnU-Net trained on the same masks. A fine-tuned Cellpose-SAM, the strongest baseline, is as accurate on average, but each of its fits takes a median of 25 minutes against 8.5 seconds, and each new mask means fine-tuning it again.

版本更新 · v2arXiv:2605.20299

物理序列建模中误泛化的机制

Mechanisms of Misgeneralization in Physical Sequence Modeling

Kento Nishi, Raphael Tang, Karun Kumar, Core Francisco Park, Hidenori Tanaka

AI 速读 基于摘要

作者发现并形式化生成式序列模型在物理轨迹规划中出现的“物理误泛化”现象,即单条轨迹看似合理但物理量(如行程距离、机械能)的总体分布偏离数据设计意图,并提出基于数据偏差核的机制解释与缓解方法。

cs.LG · cs.AI · cs.RO

查看原文摘要

Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, engineers may curate demonstrations to specify how trajectories should be distributed over a physical quantity like travel distance or mechanical energy. For example, a roboticist building a maze navigation agent might choose demonstrations whose travel distances cover a fixed range uniformly, hoping to constrain the agent's expected power usage. We find that standard deep learning can violate this intent: each generated trajectory can seem plausible on its own, but the aggregate distribution over the physical quantity is wrong. We call this failure physical misgeneralization. In this work, we identify and formalize the problem, develop and validate an account of its mechanism, and use that account to compare and design mitigations. Using controlled synthetic tasks, we show that physical misgeneralization arises when local errors typical of the model class propagate through the physical measurement to shift the recovered distribution. We estimate these errors with a data deviation kernel, and we use it to predict which physical quantity values gain or lose mass under real diffusion sequence models trained on both toy and applied trajectory generation tasks. Finally, our mechanistic interpretation helps identify which mitigations are structurally promising. We first compare interventions that modify the dataset and generative interface, then show that the mechanistic understanding we develop throughout this paper suggests a novel way to construct data representations informed by the kernel. We show that our proposed mitigation, which transforms the coordinate system under which the generator learns and samples, effectively reduces quantity drift.