CS Paper Radar

Weekly top 20

2026-W43 Oct 19 – Oct 25, 2026

Ranked from 4,679 papers submitted on 7 days. Each research area gets slots in proportion to its share of this week's papers (at least one), filled by score; near-duplicates are removed. Why

Score = weighted mean ofCitations 20%Upvotes 10%Code stars 10%Venue 15%Code/data 10%Novelty 15%Momentum 15%Substance 5%how it works
1

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search

cs.AI ·2026-10-23 ·Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler, Emad Aghajanzadeh, Manoj Rohit Vemparala +6 more
top venuecode/datahot direction
Abstract · Accepted at ICML 2026. Extended version with additional concurrent works and updated benchmark scores

Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by introducing Layer-wise Error Modeling Search (LEMS) and KFAC-SVD. LEMS advances rank allocation by introducing a layer-wise error surrogate that integrates local and global layer importance alongside a propagation bias, enabling effective global rank allocation via an ILP formulation. KFAC-SVD improves decomposition quality by utilizing token-wise statistics, mitigating the rank deficiency observed in prior Fisher-based SVD approaches. Across Mistral, Qwen3, and Llama 3 model families, we show that LEMS consistently outperforms existing search strategies, delivering significant zero-shot accuracy gains of up to 4.7 p.p. that generalize to model sizes of 70B parameters, while KFAC-SVD achieves an average perplexity improvement of 19%. Project page and code: https://lems-svd.github.io

0.80
2

Measuring undergraduate students' reliance on generative AI during problem-solving: Scale development and validation

cs.HC ·2026-10-21 ·Chenyu Hou, Gaoxia Zhu, Vidya Sudarshan, Fun Siong Lim, Yew Soon Ong
publishedhighly cited
Abstract · If you are interested in accessing the full scale and instructions, please fill in this form: https://forms.gle/xbvg9CF84o3AW1SW7

Reliance on AI describes the behavioral patterns of when and how individuals depend on AI suggestions, and appropriate reliance patterns are necessary to achieve effective human-AI collaboration. Traditional measures often link reliance to decision-making outcomes, which may not be suitable for complex problem-solving tasks where outcomes are not binary (i.e., correct or incorrect) or immediately clear. Therefore, this study aims to develop a scale to measure undergraduate students' behaviors of using Generative AI during problem-solving tasks without directly linking them to specific outcomes. We conducted an exploratory factor analysis on 800 responses collected after students finished one problem-solving activity, which revealed four distinct factors: reflective use, cautious use, thoughtless use, and collaborative use. The overall scale has reached sufficient internal reliability (Cronbach's alpha = .84). Two confirmatory factor analyses (CFAs) were conducted to validate the factors using the remaining 730 responses from this activity and 1,173 responses from another problem-solving activity. CFA indices showed adequate model fit for data from both problem-solving tasks, suggesting that the scale can be applied to various human-AI problem-solving tasks. This study offers a validated scale to measure students' reliance behaviors in different human-AI problem-solving activities and provides implications for educators to responsively integrate Generative AI in higher education.

0.77
3

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution

cs.LG ·2026-10-23 ·Yubo Ye, Maryam Toloubidokhti, Sumeet Vadhavkar, Xiajun Jiang, Huafeng Liu +1 more
top venuecode/datahighly cited
Abstract · NeurIPS 2024. 16 pages, 5 figures

The interest in leveraging physics-based inductive bias in deep learning has resulted in recent development of hybrid deep generative models (hybrid-DGMs) that integrate known physics-based mathematical expressions in neural generative models. To identify these hybrid-DGMs requires inferring parameters of the physics-based component along with their neural component. The identifiability of these hybrid-DGMs, however, has not yet been theoretically probed or established. How does the existing theory of the un-identifiability of general DGMs apply to hybrid-DGMs? What may be an effective approach to construct a hybrid-DGM with theoretically-proven identifiability? This paper provides the first theoretical probe into the identifiability of hybrid-DGMs, and presents meta-learning as a novel solution to construct identifiable hybrid-DGMs. On synthetic and real-data benchmarks, we provide strong empirical evidence for the un-identifiability of existing hybrid-DGMs using unconditional priors, and strong identifiability results of the presented meta-formulations of hybrid-DGMs. Code is available at https://github.com/GoForIt-YYB/Meta-Hybrid-VAE.

0.76
4

Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?

cs.CV ·2026-10-20 ·Xingsong Ye, Yongkun Du, Jiaxin Zhang, Chong Sun, Zhineng Chen
top venuecode/data
Abstract · Accepted as a conference paper at NeurIPS 2026

Aiming to modify textual content while preserving the original style, Scene Text Editing (STE) has significant practical value in many applications. STE typically requires paired images before and after editing for training. However, recent approaches rely heavily on synthetic paired data and complex disentanglement strategies. They struggle to faithfully capture the diversity and complexity of natural scenes, often producing artifacts or hallucinations. In this work, we challenge the common practice and investigate whether STE can be driven by turning each real sample into its own paired supervision. Concretely, we explore multiple ways to disrupt the original image (e.g., Crop, Shuffle, Mask) to construct self-paired training data, and build a strong baseline (TextRIRO}) upon a conditional diffusion architecture. Our experiments show that combining character-column shuffling with image cropping (Shuffle&Crop) effectively destroys text semantics while preserving key style cues, enabling the model to learn editing behaviors directly from the real text image. With this concise yet real-oriented design, TextRIRO achieves promising performance in both accuracy and visual realism across real-world benchmarks, substantially mitigating the synthetic-to-real domain gap. Furthermore, we leverage TextRIRO to build TextRIRO-3M, a large-scale realistic dataset for long-text recognition by concatenating edited and original images. Experimental results show that training recognition models with TextRIRO-3M significantly improves recognition accuracy, demonstrating that TextRIRO provides highly useful training resources for downstream tasks. Overall, TextRIRO lifts STE to realistic, reliable, and widely applicable new levels. Code is available at https://github.com/YesianRohn/TextRIRO.

0.76
5

MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation

cs.SE cs.AI ·2026-10-25 ·Jie Wu, Haoran Ma, Shisong Tang, Yulin Xu, Xiaoyu Kang +1 more
top venue
Abstract · Accepted at ICML 2026. 17 pages

Generating runnable front-end code from UI screenshots is a long-standing goal in automated software engineering. Existing MLLM-based methods predominantly focused on HTML/CSS, leaving multi-framework generation for React/Vue/Angular underexplored. Naively modifying prompts leads to substantial performance gaps across multi-framework and highly framework-specific error modes. To address this, we propose MulFCoder, a framework-conditioned multi-agent method that explicitly encodes framework constraints to bring multi-framework differences into a decidable rule space. MulFCoder orchestrates four agents: Grounder constructs an ElementTable, ContentTable, and macro-layout regions from detected UI elements; Planner builds a DOM-like hierarchical layout tree, produces a task schedule, and derives a framework-specific file Contract; Writer generates structured file writes or patches within a restricted edit window; Judger enforces lightweight, framework-conditioned constraints to accept or reject updates and trigger bounded repairs, preventing drift and deadlocks without expensive builds. Experiments demonstrate that MulFCoder substantially improves compilation success rate and reduces framework-specific errors, with particularly pronounced gains on Angular.

0.73
6

RSIHub: A Composable Framework for Agent-Evolution Methods

cs.AI ·2026-10-23 ·Zimu Wang, Xiaobo Wang, Siyu Ye, Jiaqi Li, Silin Chen +9 more
publishedcode/datacommunity pick
Abstract · NeurIPS 2026 Meta-Agents Workshop

Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an open-source framework for building, comparing, and extending these methods on shared infrastructure. Recipes compose reusable operators and declare mutable resources; RSIHub supplies execution, evaluation, recovery, and lineage. Researchers can focus on evolution policy while evaluation stays outside the mutable surface and results remain tied to candidates and evaluation conditions. We instantiate AHE, Hyperagents, A-Evolve, and GEPA without modifying the framework core, keeping method-specific logic in recipes and operators. We evaluate them with MiniSWE and Codex on Terminal Bench 2 and $τ^3$ Banking under fixed model and evaluator configurations. The largest observed overall pass@1 gain is 13.5 percentage points, while method rankings vary across settings and optimization gains do not always transfer to held-out tasks. RSIHub provides a common protocol for comparing evolution policies, inspectable candidate histories, and reusable components for developing new methods.

0.73
7

TIM: Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology Report Generation

cs.CV ·2026-10-19 ·Yiheng Dong, Yi Lin, Shilong Huang, Xiyan Yang, Xin Yang
top venuecode/data
Abstract · Accepted by CVPR 2026

Automatic radiology report generation (RRG) aims to translate medical images into diagnostic text, reducing radiologists' workload and standardizing clinical documentation. Nonetheless, existing approaches mainly focus on single-timepoint analysis and fail to capture temporal disease evolution across longitudinal examinations. While recent longitudinal RRG (LRRG) approaches incorporate historical data, they often combine images from different time points within a single representation space, leading to blurred semantics and inconsistent temporal reasoning. In this work, we propose a Temporal Decoupling with Iterative Mutual-Refinement Model (TIM), a two-stage framework that explicitly decouples spatial pathology from temporal progression and iteratively refines reports through mutual feedback. Stage I performs temporal-decoupled representation learning, separating temporal evolution patterns from disease-specific features and generating radiology reports for both prior and current studies. Stage II introduces a mutual report refinement mechanism that identifies diagnostic inconsistencies within prior reports and iteratively rectifies both prior and current reports through error-sensitive feedback. Experiments on the Longitudinal-MIMIC dataset demonstrate that TIM surpasses existing single-image and longitudinal baselines, achieving new state-of-the-art performance across both language and clinical metrics. Code is available at https://github.com/yihengd/TIM.

0.72
8

FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation

cs.LG ·2026-10-19 ·Yuxuan Wu, Miaopei Lin, Qiufang Ying, Lin Dan, Hao Zhao +7 more
top venuebenchmarkcode/data
Abstract · Accepted to EMNLP 2026. 28 pages, 7 figures, 8 tables. Benchmark: https://github.com/justajustin/FinHopper/

Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer is an exact typed constraint, such as an entity, date, event, or numerical indicator, that determines the next query. This strict answer-conditioned dependency makes small intermediate errors cascade into plausible but wrong search trajectories. We introduce FinHopper, a benchmark for complex financial agents with controlled reasoning depth from 1 to 6 hops, covering stocks, funds, and macroeconomic facts, with gold intermediate answers for process-level evaluation. To construct FinHopper at scale, we design a state-transition-based synthesis framework that composes verified atomic financial QA patterns into dependency-preserving chains, followed by targeted in-synthesis verification, model-ensemble checking, and public-search validation by financial experts. Experiments with 20 LLM-agent configurations show that public search tools are necessary but insufficient: performance drops sharply as hop depth increases, the best model remains far below human experts, and process-aware scoring reveals partial reasoning progress hidden by final-answer-only evaluation. The benchmark is available at https://github.com/justajustin/FinHopper/.

0.72
9

PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean

cs.AI cs.LO ·2026-10-22 ·Jiyuan Tan, Jose Blanchet, Vasilis Syrgkanis
code/datahot direction
Abstract

Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps in their own papers and turn each paper into a Lean-verified version. Starting from the LaTeX source, PaperFormalizer transcribes the paper into a dependency graph of statements, audits each statement in natural language for faithfulness, ambiguity and correctness, and then formalizes and proves the statements in Lean against Mathlib, optional domain libraries and the author's personal toolkit. Only the author knows what a statement is meant to say and how a formalization gap in a result is best fixed. The pipeline therefore stops and asks the author whenever a statement admits more than one reading, presents every repair, in natural language and TeX symbols, as a proposal that the author can accept, decline or redirect, and leaves to the author every decision that could potentially change what the paper claims. The output is an annotated and revised version of the paper, a report of the changes, and Lean code in which each declaration is linked to the statement it formalizes. The author's toolkit grows as more papers are formalized, and authors can share their verified papers so that researchers who build on them can reuse their Lean code. By making verified papers practical to produce, PaperFormalizer aims to make research that rests on mathematical proofs more robust. PaperFormalizer runs inside a coding agent (Claude Code or Codex) and is available at https://github.com/Jiyuan-Tan/PaperFormalizer. Papers with Lean code shared by users are available at https://paperformalizer.org.

0.71
10

PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets

cs.LG cs.AI ·2026-10-23 ·Joao P. A. Dantas, Andre N. Costa, Diego Geraldo, Marcos R. O. A. Maximo, Takashi Yoneyama
publishedcode/datahighly cited
Abstract · Accepted manuscript. 18 pages, 10 figures, 5 tables. Code available at https://github.com/jpadantas/poker

This work introduces PoKER, a novel probabilistic model engineered to optimize missile launch effectiveness in air-to-air scenarios, specifically within Beyond Visual Range (BVR) air combat. Unlike conventional Weapon Engagement Zone (WEZ) models that delineate zones based on static distances such as maximum, minimum, and no-escape ranges, PoKER applies machine learning to predict kill probabilities more accurately by integrating the stochastic behaviors of targets and missile miss distances. This model dynamically evaluates target behavior, greatly expanding the predictive capabilities of engagement analysis. By factoring in elements such as warhead lethality, target and shooter orientations, and the specific conditions of engagement, PoKER provides important insights into engagement dynamics and quantifies success probabilities. Consequently, it can potentially be an important tool for BVR air combat pilots, improving operational decision-making within this specialized combat domain.

0.70
11

AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking

cs.RO ·2026-10-24 ·Jianibieke Adalibieke, Qianwei Han, Xueyi Liu, Yuzhe Qin, Li Yi
top venuecode/datahighly cited
Abstract · CVPR 2026. 18 pages, 14 figures, including supplementary material. Project page: https://janebek.github.io/AdaDexTrack/

Language is a natural way to command robots, but converting a single instruction into a long-horizon, contact-rich hand-object interaction remains challenging: synthesized references are noisy, human-to-robot retargeting introduces embodiment bias, and fixed-reference tracking lets small errors snowball. We address this with AdaDexTrack, a modulator-in-the-loop framework for language-conditioned manipulation tracking. A distilled generalist tracker serves as the skill carrier, while a tightly aligned modulator performs three feedback corrections: reference modulation (continual adjustment of what to track), object-latent modulation (online adaptation of the object representation to recruit suitable skills), and positional-target modulation (small state-dependent refinements for execution). The tracker is learned via large-scale specialist to generalist distillation on a corpus of language-conditioned hand-object trajectories; the modulator is trained with RL under the same task objective, ensuring tight coupling. Across large-scale evaluations, AdaDexTrack consistently outperforms prior SOTA on unseen-trajectory and unseen-object sets in both average tracking error and success rate, demonstrating robustness and generalization. We further show zero-shot sim-to-real transfer on real hardware, where adding the modulator yields substantial gains over a tracker-only variant. AdaDexTrack reframes language-conditioned dexterous manipulation as modulated tracking, replacing the open-loop, fixed-reference tracking with in-loop modulation that adjusts the reference, object latent, and positional target, yielding drift-resistant execution from noisy text references.

0.70
12

SolarRenderer: Few-Step Generative Reference Rendering

cs.CV ·2026-10-20 ·Guian Fang, Shengju Qian, Dongyue Lu, Junchao Huang, Lutao Jiang +4 more
benchmarkcode/datahighly citedcommunity pick
Abstract · Technical Report; 28 pages, 17 figures, 10 tables; Project page at https://enderfga.cn/SolarRenderer Code at https://github.com/Enderfga/Sol…

Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and completes the appearance it leaves open. Existing renderers are tied to the representation of one engine, need tens of denoising steps or a costly distillation of their own, and learn from conditions that are not aligned with their target videos. We present SolarRenderer, a structure-conditioned video renderer that adapts a frozen MiniMax-H3 33B backbone with two lightweight LoRAs. Structural videos enter the native reference pathway of the backbone at the positions of the frames they describe, without a type identifier and described only in plain text, so that a single control LoRA follows arbitrary structural representations. Starting from a pretrained four-step LoRA, structure-guided distribution matching renders in four steps, 12.3 times faster than 50-step sampling, while preserving the learned control. A block-causal variant extends the same design to streaming and renders 768p video in real time. To train the model, we build a frame-aligned corpus of 136K clips from game engines, simulators, and YouTube videos. Experiments on an in-distribution test set and a generalization benchmark of 16 structural representations show that SolarRenderer achieves state-of-the-art results across both, and generalizes to 11 unseen representations, including pose skeletons, drawings, and point clouds.

0.70
13

The Emergence and Sparsification of a Syntactic Circuit

cs.CL ·2026-10-23 ·Qing Yao, Sasha Boguraev, Tiago Pimentel, Kyle Mahowald
top venue
Abstract · 26 pages, 7 figures, EMNLP 2026

To understand the emergence of grammatical behavior in language models, we track circuits for subject-verb number agreement in pythia-1b and ten seeds of pythia-410m across training. We find that subject-verb agreement is learned early, and is initially handled by a diffuse collection of neurons. However, after agreement behavior has stabilized, the mechanisms responsible for it continue to reorganize. The attention heads which mediate agreement often shift during training: in the case of pythia-1b, behavior is controlled by two heads early in training but by a third (different) head later. Furthermore, the circuit shrinks over training, with pythia-1b's final circuit being strikingly sparse. We take these results to be informative about how linguistic knowledge emerges and is represented in a language model.

0.69
14

When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs

cs.CR cs.AI ·2026-10-19 ·Rui Melo, Andre Catarino, Claudia Mamede, Corina Pasareanu, Rui Abreu
top venuehot direction
Abstract · Accepted at EMNLP Findings

Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-15B parameters on C programs using three datasets (DELTASECOMMITS, SVEN, and PRECISE-BUGS), comparing two diagnostic tasks on the same representations: identifying what patterns the code instantiates, and determining whether it is vulnerable. Models encode the first with high fidelity. Under the studied paired C-code datasets and linear-probing setup, vulnerability information is more accessible as a paired relational signal-whether code A is riskier than code B-than as a globally separable categorical label. This structural difference has implications for classification: the model reliably ranks which code is riskier but standard classifiers on isolated samples achieve limited accuracy because vulnerable and secure samples form overlapping distributions in representation space.

0.68
15

Enhancing IoT Network Reliability through Antenna Diversity in Real-World Scenarios

cs.NI eess.SP ·2026-10-21 ·Marco Niederberger, Yanick Schoch, Michel A. Nyffenegger, Christian Gwerder, Hans-Dieter Lang
publishedunusual
Abstract · 5 pages, 8 figures, 1 table

Antenna diversity in Internet of Things (IoT) devices is explored to address challenges associated with fixed device orientation and interference from nearby metallic objects, which can degrade wireless network performance. Integrating multiple antennas with different polarizations can significantly enhance signal quality and network reliability. Experiments demonstrated significant improvements in link quality, with gains exceeding 30 dB in received signal strength for specific scenarios. Already the addition of a second PCB-based antenna alone, resulted in a 17 dB improvement. These findings suggest that the added complexity in hardware and software to incorporate antenna diversity could well be justified by the resulting enhancements in network stability for real-world applications.

0.68
16

Which Answer Did the Seventeen-Year-Old Write? A Behavioral Case Study of Author-Age Misattribution, Miscalibrated Confidence, and Non-Corrective Self-Explanation in Six Frontier Language Models

cs.CL ·2026-10-22 ·Brianne Lee
code/data
Abstract · 15 pages, 6 tables. Code and data: https://github.com/BraveAnn011/llm-author-misattribution

Three students answered the same exam prompt by hand: "What is happiness? Are you happy?" Their ages, recorded at collection, are 17, 28, and 45. The 17-year-old's answer is hedged and formally phrased. Asked to match each answer to an age and gender label, most frontier language models confidently assign it to an adult. This paper reports a structured case study of that failure across six models: Claude Fable 5, Gemini 3.1 Pro, GPT-5.6 Sol, Grok 4.5, GPT-4o (2024), and DeepSeek V4. We ran 1,081 API sessions and scored 3,225 responses across six experimental conditions that manipulate framing, disclosure format, and audience-awareness instruction. Three of six models perform at or near chance (1/3) on the matching task while reporting 73-88% mean confidence. The youngest writer's answer is misattributed to an adult in up to 90% of trials. Removing the multiple-choice scaffold collapses accuracy further: three models never place within three years of the true age once open-ended estimation is required. Institutional framing ("a community-college biology final") significantly degrades the best-performing model's accuracy; a neutral label does not. A single audience-awareness instruction significantly improves one model (+21 points) and moves another to ceiling, with no detectable effect on the three weakest models. Stated confidence is uncorrelated or inversely correlated with correctness for five of six models. After ground truth is revealed, one model names its own stereotyping in 68 of 114 explanations, yet shows the lowest accuracy and highest confidence of any model under blind presentation: articulate retrospective diagnosis that does not track the quality of its judgments. This is a three-item, single-topic, single-language case study meant to isolate a mechanism, not to estimate a population bias rate. Data, code, and raw model outputs are publicly released.

0.68
17

Multimodal Reranking Is a System One Decision

cs.IR ·2026-10-20 ·Zhuchenyang Liu, Yao Zhang, Yu Xiao
code/datahighly cited
Abstract · Position paper. 19 pages (9 main), 2 figures, 12 tables. Code: https://github.com/Ryenhails/rerank-as-decision

Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to score the candidates of a query. Scoring options is not specific to reranking. System One decision models such as Jev map a state and a typed question to one probability per option without generating text, and general models can make such decisions with little or no training. Reranking is one such decision, with the query and its candidates as the state and the candidates as the options. We therefore argue that a general VLM can serve as a multimodal reranker through System One decisions, and that decision tuning can improve its reranking. We ask a VLM one choice question over the top 16 candidates of a first-stage retriever and rank the candidates by the probabilities of their labels, read from one forward pass. On MMEB-V2 image retrieval, this choice scores 5.4 to 7.3 hit@1 above a yes/no question per candidate, and the yes/no question falls below the first stage. With the choice, zero-shot Qwen3.8-27B beats the supervised Qwen3-VL-Reranker-2B on all three benchmarks and comes within 1.6 points of Reranker-8B on each. It matches Reranker-8B on MMEB-V2 visual documents (84.79 vs. 84.78 nDCG@5), at 1.1 to 1.5 times its latency. JEV-27B-VL, the same backbone tuned on text decisions only, improves page reranking by 0.6 to 1.1 points, with gains on most tasks (sign test, p <= 0.017), and leaves natural images unchanged. The zero-shot model is larger than the supervised rerankers and of a newer generation, so these comparisons are confounded; we discuss this and other alternative views, and the experiments that would test the position.

0.67
18

SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model

cs.RO ·2026-10-20 ·Qiayuan Liao, Yiyang Shao, Junfeng Long, Kevin Zakka, Roberto Horowitz +2 more
publishedbenchmarkhighly cited
Abstract · Accepted at CoRL 2026 (Oral). Project website: https://supermimic.github.io

Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive. Current pipelines use model-free reinforcement learning, either merging per-motion specialists through lossy distillation, or brute-forcing a single policy with cluster-scale compute. SuperMimic amortizes learning across all motions with one differentiable world model of their shared dynamics, fit from logged transitions of a standard rigid-body simulator. The world model and the tracking policy train together in one loop, and backpropagation-through-time over short imagined rollouts gives the policy analytic gradients. Fast imagined rollouts and analytic gradients make policy learning efficient. In 3 hours on a single GPU, SuperMimic surpasses the return of a state-of-the-art motion tracker baseline trained for 7 days on 128 GPUs. It reduces GPU-hours by more than $1000\times$ and fails on only 25 of 129,514 benchmark motions, versus 179 failures for the baseline. After 9.8 hours on two GPUs, SuperMimic achieves zero failures. From 1 to 264 hours of motion, the world model's prediction error stays stable, and GPU-hours to a target return grow slowly. Our policy transfers to a physical Unitree G1 across diverse and acrobatic motions. SuperMimic removes compute as the bottleneck to scaling humanoid whole-body control, making it practical to measure motion-tracking scaling laws.

0.63
19

Space Complexity of Reachability in Simple Path Graphs

cs.CC ·2026-10-20 ·Krishnamoorthy Dinesh, Chandana Sasidharan
published
Abstract · 17 pages, 9 figures

One of the central questions in space complexity is whether nondeterministic logspace computations ($\textsf{NL}$) can be simulated in unambiguous logspace ($\textsf{UL}$). A stronger notion, \emph{reach unambiguity} ($\textsf{RUL} \subseteq \textsf{UL} \cap \textsf{co}\textsf{UL}$), requires every configuration reachable from the start to have exactly one computation path (Buntrock et.al. 91). While directed graph reachability is $\textsf{NL}$-complete, planar graph reachability is in $\textsf{UL}$ and undirected graph reachability is in deterministic logspace ($\textsf{L}$). In this work, we study the space complexity of reachability problem for restricted directed graph families and show the following. - For reach unambiguous graphs (graphs with at most one path from start vertex to every vertex), Lange (Lange 97) showed that reachability is in $\textsf{RUL}$. As our main result, we show that for simple path graphs (introduced in Kannan et.al. 08), which contains reach unambiguous graphs), where each vertex has at most one simple path from the start, we show that the reachability problem lies in $\textsf{UL} \cap \textsf{co}\textsf{UL}$. - Our first result can also be equivalently stated as: the recognition problem for simple path is in $\textsf{UL} \cap \textsf{co}\textsf{UL}$ if and only if the reachability problem restricted to simple path graphs is also in $\textsf{UL} \cap \textsf{co}\textsf{UL}$. Inspired by this, we investigate the complexity of graph recognition versus graph reachability for graph classes. Observe that for any graph class, solving reachability (for the class) also solves the recognition problem for that class. We show that for reach unambiguous graphs, solving recognition is as hard as solving reachability (making both of them $\textsf{RUL}$-complete). (Abstract shortened to meet arXiv limits)

0.63
20

Robotic Physical Comparison of Biologically Motivated and Counterfactual Sensory Arrangements using Biomimetic Skin

cs.RO ·2026-10-19 ·Akihiro Miki, Shun Hasegawa, Yoshimoto Ribayashi, Yuta Sahara, Kento Kawaharazuka +1 more
publishedcode/data
Abstract · Published in Bioinspiration & Biomimetics (IOP Publishing). Project page: https://poyotamu000.github.io/biomimetic-skin-sensory-arrangements…

Human skin contains diverse mechanoreceptors, including Merkel cells and Pacinian corpuscles, each localized in specific regions. Although their spatial organization is known to be shaped by molecular signaling and neural induction during development, experimentally examining its functional significance under controlled conditions in living systems remains challenging. In particular, physically comparing alternative receptor arrangements that do not occur biologically is difficult. In this study, we developed a layered biomimetic robotic skin designed to mimic key structural features of human skin tissue by embedding receptor-analog sensors within compliant soft media. Using this platform, we implemented both biologically motivated and counterfactual sensory arrangements and quantitatively evaluated their performance across three passive tactile tasks: detection of weak contacts, a two-point discrimination-like assessment, and texture identification. Arrangements reflecting key features of the biologically motivated sensory organization exhibited higher performance than the alternative configurations examined. This study addresses a biological question concerning how spatial organization influences tactile function by presenting a biomimetic robotic approach that enables physical and empirical comparison of biologically motivated and counterfactual sensory arrangements that are difficult to investigate in living systems.

0.61