Discrete Mathematics
Maximum Edge Open Packing on AT-Free, Chordal, and Convex Bipartite Graphs
Gautam K. Das and Kamal Santra
An edge open packing is a set of edges whose endpoints induce a disjoint union of
stars. We study the problem of finding a maximum edge open packing in AT-free, chordal, and convex bipartite graphs. For AT-free graphs, we use the oriented
star-conflict graph $A_G$, introduced by Das and Santra, for which $\rho_e^o(G)=\alpha(A_G)$, and prove that $A_G$ is AT-free whenever $G$ is AT-free. Consequently, a known maximum independent set
algorithm for AT-free graphs yields an $O(n^2+m^4)$-time
algorithm for Maximum Edge Open Packing, where $n$ and $m$ denote the numbers of vertices and edges of $G$, respectively. For chordal graphs, we develop an $O(n^4)$-time dynamic programming
algorithm over a nice tree decomposition derived from a clique tree, exploiting the structural fact that the endpoint set of an edge open packing intersects every clique in at most two vertices. Finally, for convex bipartite graphs, we obtain an $O(n^4)$-time dynamic programming
algorithm based on two boundary indices that separate consecutive
star components. This result extends the previously known
algorithm for biconvex bipartite graphs and, in particular, provides an improved explicit running-time bound for that class.
Read the full abstract ▾
Robotics
Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation
Awomo-PhysicalRSI Team, Danjiao Ma, Enhui Ma et al. (+21 more)
Generating useful
robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution. We presentAwomo-SimDataEngine, an agentic system that connects asset and scenegeneration to
robot demonstration synthesis. Shared asset services providerigid and articulated objects, including structure-grounded part and jointgeneration with ISArt. Scene generation supports two complementary routes:Unravel reconstructs editable scenes from images, while SimForge buildssingle-room and multi-room environments from text. A graph-native harnesscoordinates construction, validation, andbounded repair, routing failures to the responsible module while retainingunaffected scene state. PolicyForge binds validated worlds to tasks and robotembodiments to produce replayable demonstrations. Evaluations cover assetgeometry, scene quality, and downstream policy learning. On MuJoCo-basedLIBERO-Plus, co-training with Isaac Sim demonstrations improves the overallsuccess rate of a World-Action Model (WAM) from $77.17\%$ to $89.43\%$. Goal and spatialsuccess improve by $31.66$ and $6.25$ percentage points, respectively.These results support the utility of the generated data for cross-simulatorpolicy training, with more limited gains on long-horizon tasks.
Read the full abstract ▾
All authors Awomo-PhysicalRSI Team, Danjiao Ma, Enhui Ma, Haohan Liu, Heng Jia, Hui Shan, Jianhua Xu, Jiahuan Zhang, Jiangdi Xu, Kaiwen Guo, Kaicheng Yu, Linwei Zhang, Liyang Jin, Maochun Luo, Pengyao Niu, Shiwen Li, Shuangyu Feng, Tong Zhang, Tianheng Wang, Xin Wang, Xiangru Huang, Yongqiang Huang, Zhaozhi Wang, Zijian Ma
Computer Vision · Cross-listed from eess.IV
Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models
Xinye Yang, Zhusi Zhong, Scott Collins et al. (+3 more)
Medical
vision-
language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and
benchmark construction, yet most studies treat these factors in isolation. We introduce a reliability stress test for chest X-ray interpretation built on two balanced
datasets (a private report-backed set and a curated MIMIC subset). Three medical VLMs (CheXagent, MedGemma-4B, and MedGemma-27B) are evaluated across three
prompt styles and two workflows (single-VLM and multi-
agent), producing 36 configurations. We show that exact-match accuracy alone can overstate the effectiveness of conservative models that default to "Normal" predictions. Diagnostic reliability also depends heavily on model family and scale: multi-
agent reasoning helps some configurations but hurts others. Building on these observations, we propose a decision-time routing framework that selectively escalates to multi-
agent inference only when beneficial, improving the cost-quality trade-off over fixed workflows. Our results highlight the need for evaluation protocols that jointly consider
prompt sensitivity, failure-mode diversity, and workflow choice before clinical deployment.
Read the full abstract ▾
All authors Xinye Yang, Zhusi Zhong, Scott Collins, Grayson Baird, Xuyu Wang, Zhicheng Jiao
Computer Vision · Cross-listed from eess.IV
Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging
Xinye Yang, Zhusi Zhong, Scott Collins et al. (+7 more)
Emergency chest X-ray (CXR) triage has a structural modality gap: reports arrive after triage decisions, yet
multimodal foundation models require image-text inputs. We present Variational Risk Minimization (VRM), a
distillation framework that treats LVLM-generated report variants as Monte Carlo samples of latent clinical interpretations. Rather than distilling from a single teacher target, VRM learns from a variationally marginalized teacher distribution, enabling uncertainty-aware supervision under missing-modality constraints. Under matched encoder families, VRM outperforms direct fine-tuning baselines and improves calibration with strong recovery from hallucinated supervision. Marginalized supervision reduces report-selection instability. In our compact edge-student instantiation, a confidence-gated cascade reaches AUC 0.941 at 103ms average latency with 20.3% cloud escalation, yielding an explicit reliability-latency operating point for cloud-edge clinical workflows.
Read the full abstract ▾
All authors Xinye Yang, Zhusi Zhong, Scott Collins, Michael Bernstein, Grayson Baird, Terrence Healey, Michael Atalay, Mahesh Jayaraman, Xuyu Wang, Zhicheng Jiao
Machine Learning
From Mathematical to Executable Certificates for Machine Unlearning
Ziyu Zhao, Xinyu Wang, Xiaowen Chang et al. (+1 more)
Machine unlearning is needed when data must be removed because of deletion requests, outdated records, or data-quality concerns, while retraining from scratch can be costly. Certified machine unlearning methods provide mathematical guarantees, while deployed systems release concrete finite-precision artifacts produced by software. To bridge the gap between mathematical guarantees and practical deployment, we introduce Executable Release Certification (ExecCert), a release-time layer that certifies the candidate artifact considered for release. ExecCert either closes a method's native certificate for the executed candidate or applies Retraining-Reference Release Verification (RRV) to certify fidelity to current retain-set retraining. Sequential deletion makes the latter nontrivial because the exact retain-set reference and the stored numerical state evolve separately. For frozen representations with a mutable ridge head, we develop an incremental realization of RRV that maintains certified evidence across deletion requests rather than reconstructing it at each release. On four published unlearning implementations, ExecCert preserves valid certificates, changes release decisions, tightens conservative bounds, and identifies the retraining-reference fidelity supported by concrete outputs. In sequential-service experiments, RRV eliminates false releases caused by stored-equation verification while closely tracking realized error, and incremental certification remains cheaper than both fresh and maintained verified-factor alternatives once release checks become sufficiently frequent.
Read the full abstract ▾
All authors Ziyu Zhao, Xinyu Wang, Xiaowen Chang, Yixuan He
Artificial Intelligence
Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses
Jiawei Li
Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with class probabilities, promising large cost and latency savings over LLM calls. We present a paired evaluation of an open-weight (Laya) and a hosted (Jev) System-1 model on 11
agent decision points built from 18 public sources: 7,283 base cases plus 6,640 robustness variants, with byte-identical inputs, paired tests, and cross-hardware and cross-day reproducibility checks. Jev is significantly more accurate on 9 of 11 decision points (+10.8 to +46.0 pp). Neither model beats chance on zero-shot model routing, and they tie on RAG relevance gating. Laya changes 30% of its answers when the option order is reversed and degrades sharply with many or similar candidates (31% at 50 nearest-neighbour tools, vs. 98% for Jev on items with a unique correct tool). We also audit our own pipeline. Three analysis errors and one design confound distorted headline deployment claims: an omitted pre-screen cost (reported 23.9% saving, actual 4.3%), gate accuracy reported as end-to-end quality (58% vs. 98%), in-sample thresholds (5% target, up to 17% held-out misses), and a "channel effect" on injection false positives that vanishes with channel-native content. Two other suspected confounds did not change the conclusions. All cases, raw outputs and analysis code are available at https://github.com/David-DL-Space/sys1-eval.
Read the full abstract ▾
Computer Vision · Cross-listed from eess.IV
Event-guided Neural Video Compression
Jiyun Kong, Jungwoo Kim, Enes Eray Demirtas et al. (+2 more)
Neural
video codecs derive motion and temporal contexts mainly from RGB frames, leaving room for cross-modal guidance from complementary temporal observations. Event streams can provide such observations by recording brightness changes between frames. In this work, we propose an Event-guided Neural
Video Codec (ENVC) that uses events shared by the encoder and decoder to improve RGB compression efficiency. For motion coding, ENVC forms an event-guided motion prior and codes the remaining motion residual. For frame coding, an event-conditioned predictor supplies multi-scale features for gated temporal context refinement. To support training and evaluation on standard
video datasets, we synthesize paired RGB-event data and assess its predictive utility through comparisons with real events. Across six
benchmarks, ENVC achieves average BD-rate savings of 39.13% using PSNR-RGB and 67.63% using LPIPS relative to DCMVC. Further analyses show that our gains persist on large-motion sequences and that ENVC effectively learns to integrate event information. These results demonstrate the potential of events as a complementary modality for reducing the RGB coding rate. Our model and code are available at https://github.com/kjungwoo03/ENVC.
Read the full abstract ▾
All authors Jiyun Kong, Jungwoo Kim, Enes Eray Demirtas, Touradj Ebrahimi, Jong-Seok Lee
Computer Vision · Cross-listed from eess.IV
ZAGNet: Zone-Aware Graph Aggregation Network for Patient-Level Lung Ultrasound Diagnosis
Li Chen, Shubham Patil, Rashid Al Mukaddim et al. (+3 more)
Patient-level lung ultrasound (LUS) diagnosis requires integrating findings acquired across multiple anatomical zones, yet clinical examinations frequently involve variable and incomplete scanning protocols with missing zones. Existing diagnostic AI methods primarily analyze individual frames or
video loops, relying on heuristic aggregation strategies such as max or mean pooling that ignore inter-zone relationships for patient-level inference. This paper presents ZAGNet, a Zone- Aware Graph Neural Network that represents temporally tracked pathology findings as graph nodes connected by anatomical zone adjacency. A graph
transformer network propagates contextual information across neighboring lung regions, while a virtual global node aggregates graph-level features to predict patientlevel consolidation and pleural effusion using only patient-level supervision. ZAGNet accommodates missing zones by computing on a graph structure without fixed input format or size. We evaluate ZAGNet on a multicenter
dataset of 714 subjects (20,256 LUS
video loops) with exams varying from 4 to 16 zones across anterior, posterior, and lateral thoracic regions. For consolidation diagnosis, ZAGNet achieved an AUC of 0.803 compared to 0.677 (max pooling) and 0.674 (mean pooling). For pleural effusion, AUC increased to 0.893 from 0.804 (max pooling) and 0.815 (mean pooling). These represent improvements of up to 19% and 11% for consolidation and pleural effusion respectively. The results demonstrate that graph-based inter-zone
reasoning provides an effective and clinically consistent framework for automated patient-level LUS assessment.
Read the full abstract ▾
All authors Li Chen, Shubham Patil, Rashid Al Mukaddim, Jochen Kruecker, Balasundar Raju, Alvin Chen
Formal Languages and Automata · Cross-listed from math.CO
Shuffle squares in smooth binary words and the Kolakoski sequence
Kory Kilpatrick
A binary word is a shuffle square if its positions can be partitioned into two identical subsequences. A finite word over $\{1,2\}$ is smooth if repeated finite run-length differentiation remains binary until the empty word is reached. This paper proves that every smooth binary word in which both letters have even multiplicity is a shuffle square once its length is at least $18$. There are exactly $34$ exceptions, all of length at most $16$. The infinite part of the proof is a parity-return atom induction: a smooth even-Parikh word factors uniquely into smooth parity atoms, and every such atom has length at most $8$. A finite, independently checkable certificate handles lengths $18$ through $40$. As a consequence, a nonempty prefix of the classical Kolakoski sequence is a shuffle square if and only if both symbols occur an even number of times and its length is not $4$ or $8$. There are infinitely many such prefixes. In fact, the entire infinite Kolakoski sequence can be partitioned into two identical infinite subsequences with monochromatic blocks of uniformly bounded length.
Read the full abstract ▾
Computer Vision
Moore, Escher, Penrose: A Conformal Golden Braid
Sophia Feldman and Assaf Shocher
I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of an exhibition that features himself. How can this be? Perhaps I am not far removed from Einstein's curved universe.” So wrote M.C. Escher about his 1956 lithograph Print Gallery. Nearly half a century later, a mathematical analysis related its geometry to an untwisted source image through a conformal power map $z \mapsto z^\alpha$, $\alpha \in \mathbb{C}$. Building on this construction, we use a frozen text-to-image
diffusion model to generate new self-referential scenes. Prompting alone does not enforce the recursion, while a post-hoc transformation can leave structures poorly connected. Applying the transformation during sampling is also insufficient: the denoiser may "repair" the intended distortion or drift out of the prescribed geometry. We construct a generalized inverse $T^\dagger$ of the non-invertible image transformation $T$, adapted to its recursive constraint. In the idealized formulation, the Penrose identity $TT^\dagger T = T$ makes $TT^\dagger$ an idempotent projection onto geometrically admissible images. Yet denoising only the transformed image remains an out-of-distribution task, even with projection. We therefore braid denoising steps with $T$ and $T^\dagger$: source-space steps develop the untwisted scene, while transformed-space steps refine its appearance and connections in the final geometry. We generate Print Gallery-like compositions and explore further transformations. Rather than distorting a finished image, we let the scene and its distortion develop together.
Read the full abstract ▾
Computer Vision
Sphere Encoder 2
Kaiyu Yue, Sean McLeish, Ruchit Rawal et al. (+3 more)
Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere. We identify two limitations of the original formulation that reduce its generation quality. First, random points concentrate near the equator relative to the pole on an encoded latent, but the training rotation never reaches this region, leaving a gap that limits one-step generation. Second, training for generation with pixel-wise reconstruction loss encourages the decoder to average over plausible images, producing blurry images that lack high-frequency details. We present Sphere Encoder 2 to address both limitations, substantially improving image generation quality while maintaining the speed and simplicity of a autoencoder. Models are released at https://github.com/kaiyuyue/sphere2.
Read the full abstract ▾
All authors Kaiyu Yue, Sean McLeish, Ruchit Rawal, Brian Bartoldson, Menglin Jia, Tom Goldstein
Computer Vision
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
Ramazan Fazylov, Stamatis Lefkimmiatis and Ivan Laptev
3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bottleneck and show that the animation of pretrained avatar models can be closely approximated by a linear combination of identity-independent blendshapes. Building on this finding, we introduce GALA (Gaussian Animation via Linear Approximation), a
distillation method that replaces per-frame heavy neural decoding with a shallow coefficient predictor and a linear blend. To improve fidelity and reduce
memory requirements, we propose to construct the basis using block-local PCA under a rendering-aware metric and a
memory budget. Our method learns a shallow MLP network to predict blendshape coefficients and applies to various animation architectures without retraining original models. We validate GALA by accelerating the inference of three distinct avatar models for 3D animation of facial expressions and full-bodies with clothing dynamics. Across these models, our
distillation generalizes to held-out identities and reduces CPU animation cost by up to three orders of magnitude while preserving most of the rendering quality. Excellent results of our method confirm the shared linear structure of learned avatar representations and enable highly efficient and accurate animation at frame rates reaching up to 60fps on mobile devices. Project page: https://ramazan793.github.io/gala/
Read the full abstract ▾
Computation and Language
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Pengfei Li, Naufal Suryanto, Sicheng Zhang et al. (+1 more)
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks, and do not directly measure LLMs' ability to generate executable commands for real-world cybersecurity tools. This gap is critical because cybersecurity operations rely on strict command-line interfaces (CLIs), where minor syntax errors, incorrect flag–value bindings, or argument misordering can invalidate execution. We introduce KaliBench, a fine-grained
benchmark and
dataset for natural-
language–to–CLI translation on Kali Linux, comprising 8,504 query–command pairs spanning 1,642 tools across 23 capability dimensions and 5 security phases. KaliBench is constructed via a manuscript-grounded pipeline with deterministic canonicalization and alias-aware evaluation, enabling precise and reproducible assessment of tool selection and argument construction. To ensure both semantic correctness and practical executability, we develop a multi-stage verification pipeline that combines LLM-based validation, sandboxed terminal execution, and human-in-the-loop refinement. Building on these fine-grained, deterministic signals, KaliBench further enables runtime-free verifiable rewards for training. Across three evaluation modes and 24 configurations of general-purpose and security-focused open-weight models, no open-weight model exceeds 42% exact-command accuracy in the unrestricted setting, highlighting the difficulty of accurate CLI-based cybersecurity tool use without explicit tool hints. We further show that supervised fine-tuning and reinforcement learning with verifiable rewards derived from KaliBench significantly improve an 8B model and achieve performance comparable to a 685B MoE model.
Read the full abstract ▾
All authors Pengfei Li, Naufal Suryanto, Sicheng Zhang, Muzammal Naseer
Computer Vision
PROWBench: Do Video Models Render What the Program Specifies?
Zheng-Hui Huang, Guixu Lin, Yu-Ju Tsai et al. (+6 more)
Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-generation game engines. However, their visual adherence to explicit rules and interactions remains insufficiently evaluated. Existing
benchmarks assess visual quality, controllability, and instruction or physical adherence, but rarely test fidelity to fine-grained, program-specified world events. We introduce PROWBench, comprising 170 programmatically constructed episodes and 600 proxy
videos covering diverse scenes and interactions. PROWBench logs entity states and timestamped events, including those outside the camera's field of view, as replayable world records, from which it renders synchronized views and proxy representations. This enables generated
videos to be checked against the observable consequences of program execution. An extensible framework constructs scenes, controls behaviors, and can render each camera view in different representations, such as coarse 3D, and bounding boxes. The
benchmark covers first- and third-person perspectives, with synchronized multi-view observations available for a subset of episodes. Grounded in these records, PROWBench evaluates entity control, long-horizon
memory, and, with two VLM-based metrics, Logic-Render
Alignment and Interaction Success Rate, adherence to the prescribed timeline and the visual realization of timestamped engine-recorded events.
Read the full abstract ▾
All authors Zheng-Hui Huang, Guixu Lin, Yu-Ju Tsai, Jian-Kai Zhu, Fengbo Lan, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang
Robotics
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
Yen-Jen Wang, Haozhe Jiang, Shuying Deng et al. (+7 more)
Building reliable
robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of
robot execution systems without updating model weights. RPG identifies manipulation capabilities in an offline
dataset and constructs related practice tasks in simulation. During practice, RPG uses execution feedback, privileged simulator state, and available
dataset videos to diagnose failures. It develops new reusable symbolic skills, refines existing skills, and revises the system
prompt based on these diagnoses. Cross-task evaluation tests individual candidate changes and merged revisions before they are retained for reuse. At test time, a
multimodal LLM uses the resulting system
prompt and skill library to coordinate perception and
robot control. On held-out initializations of 22 manipulation tasks, RPG improves task success from 28.6% after the first practice round to 95.0% after 15 rounds, outperforming all evaluated baselines, including ASPIRE (75.5%) and CaP-
Agent0 powered by GPT-6 Astra Pro (60.0%). After a common calibration and hardware-adaptation procedure, the frozen system succeeds in all 30 physical trials, with ten trials on each of three tasks. Project Website: https://rpg-
robot.github.io/
Read the full abstract ▾
All authors Yen-Jen Wang, Haozhe Jiang, Shuying Deng, Haoru Xue, Weirui Ye, Rocky Duan, Nika Haghtalab, S. Shankar Sastry, Pieter Abbeel, Haozhi Qi
Computer Vision
Embedding Prediction Helps Image Generation
Sihan Xu, Ji Xie, Zilin Wang et al. (+2 more)
In
diffusion transformers, a class label or a text
prompt is embedded once, and the same condition is reused at every denoising step. We ask whether predicted
embeddings can serve as this condition instead. Next-
Embedding Predictive Autoregression (NEPA) trains a
Transformer to predict the next continuous
embedding in a sequence. In generation, the clean image follows the noisy image, so its
embeddings are the next
embeddings after the condition and the noisy image. We train a NEPA model to predict them all at once with Multi-
Embedding Prediction, and in
Embedding Conditioned Generation, a DiT generator is conditioned on these predictions, recomputed at every denoising step, so the conditioning signal adapts to the current noisy state. Experiments on class-conditional ImageNet $256\times256$ study the condition of the generator, the design of Multi-
Embedding Prediction, and the scaling of both models. The NEPA model adds a second network to every sampling step; with it, and combined with REPA, our final model, NEPA-DiT-XL, reaches an FID of 1.32 using about a third of the training compute of REPA.
Read the full abstract ▾
All authors Sihan Xu, Ji Xie, Zilin Wang, Hui Shen, Stella X. Yu
Artificial Intelligence
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
Sohyeon Kim, Yoonho Lee, Bo Liu et al. (+11 more)
What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. To study this skill, we draw on researchers who know firsthand which earlier work advanced their completed projects, with papers serving as pointers to the ideas within. Using our automated pipeline that makes author annotation scalable, we build ScholarCatalyst by having 184 lead authors of 207 recent computer science papers label which candidates did or could have advanced their project, each with a detailed rationale. We introduce a
retrieval task with author-provided judgments: given an initial research question, retrieve these papers from only the literature available when the project began. Agentic search does no better than
embedding retrieval (0.42 vs. 0.48 Recall@20) despite calling that same retriever as a tool. Even an
agent built on Claude Fable 5.1, which may have seen the completed papers during training, reaches only 0.51 R@20. These results highlight the need for new training recipes that equip models with expert intuition for searching broad corpora. We envision ScholarCatalyst as a step toward scientific
agents that can take a half-formed idea and point to the prior research it needs.
Read the full abstract ▾
All authors Sohyeon Kim, Yoonho Lee, Bo Liu, Dayoon Ko, Rulin Shao, Seungone Kim, Graham Neubig, Pang Wei Koh, Aakanksha Chowdhery, Akari Asai, Omar Khattab, Yejin Choi, Gunhee Kim, Chelsea Finn
Computer Vision
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Tianjiao Yu, Xinzhuo Li, Yifan Shen et al. (+4 more)
High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local
tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. We introduce SILSA, a
topology-aware 3D generation framework that represents shapes with compact sliding-window slice latents. Instead of generating expensive voxel
tokens, SILSA uses a fixed set of overlapping slices along the three canonical axes, where each
token summarizes a local depth window to preserve cross-sectional continuity and support single-stage rectified-flow generation. A Slice VAE encodes oriented surface samples into multi-axis slice latents and reconstructs them with a sparse volumetric decoder, while a Volumetric Anchor
Lattice coordinates directional slice streams through a shared 3D workspace. To preserve structural correctness, we introduce slice-level
topology supervision that matches persistence diagrams and aligns Betti transitions across neighboring slices. Experiments show that SILSA improves structural fidelity while substantially reducing generation cost. SILSA improves PSNR by $8.7\%$, coverage by $5.96$ absolute points, and Betti error by $9.2\%$ over the strongest baseline, while using $70.0\%$ fewer
tokens than the next-most compact baseline and over $98\%$ fewer
tokens than sparse or hierarchical tokenizers, effectively reducing training
memory by $40.4\%$ and inference time by $58.5\%$. Qualitative results further show improved preservation of thin structures, repeated components, and long-range connectivity.
Read the full abstract ▾
All authors Tianjiao Yu, Xinzhuo Li, Yifan Shen, Ying Shen, Kiet A. Nguyen, Adheesh Sunil Juvekar, Ismini Lourentzou
Artificial Intelligence
VISTA: A Visual Harness for Reasoning in an Interactive World
Qiushi Han, Keya Hu, Linlu Qiu et al. (+2 more)
We show that
multimodal models possess strong
reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a general-purpose
multimodal model long-horizon
vision. VISTA allows the model to directly perceive the environment through visual observations and maintains a lossless visual
memory that preserves past observations in their original form. The model can actively retrieve these observations and reorganize its visual input as it reasons. On ARC-AGI-3, VISTA improves Claude Opus 5.0's Relative Human Action Efficiency score from 40.68 to a perfect 100.00, with the model completing all 25 public games using 57.4% fewer actions than first-time human participants. VISTA's simple design also allows it to extend naturally to diverse visual environments with minimal adaptation. Across three additional
benchmarks covering a diverse range of visual games and puzzles, it substantially outperforms baselines using the same underlying model with minimal harnesses. Our results highlight VISTA's potential as a general-purpose visual harness for advancing
multimodal agents in complex visual environments.
Read the full abstract ▾
All authors Qiushi Han, Keya Hu, Linlu Qiu, Cathy Wu, Kaiming He
Machine Learning
TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning
Jichao Jiang, Cristian McGee, El Houcine Bergou et al. (+2 more)
Full-parameter fine-tuning of large
language models (LLMs) incurs substantial optimizer state
memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches either compress optimizer state, abandon first-order gradients, or change the update geometry while retaining dense state. The recently introduced
Muon optimizer reduces optimizer
memory through
matrix-valued updates. Still, its geometry differs from AdamW and can lead to performance degradation when fine-tuning AdamW-pretrained models. To reduce optimizer
memory without sacrificing accuracy or computational efficiency in LLM fine-tuning, we propose Ternary Absolute-max Column-wise One-sparse optimizer, or TACO, which follows
Muon's operator-norm steepest-descent view but takes the
geometric route further. TACO computes the exact steepest-descent direction under a dimension-normalized $1\to1$ operator norm by selecting the sign of the largest magnitude entry in each column of two-dimensional weight
matrices. This retains first-order gradients while making optimizer state
memory nearly negligible. Our practical TACO optimizer maintains only a small set of low precision gradient components per column, reducing persistent optimizer state by $174\times$ relative to AdamW8bit (from 27.7 GB to 0.16 GB) and peak training
memory by $2.9\times$ (from 80.6 GB to 27.5 GB) on OPT-13B, while achieving comparable accuracy and runtime. TACO further enables full-parameter fine-tuning of 30-32B-parameter models on a single 80 GB H100 GPU across multiple model families and tasks.
Read the full abstract ▾
All authors Jichao Jiang, Cristian McGee, El Houcine Bergou, HanQin Cai, Aritra Dutta
Machine Learning
FERPO: Forward Entropy-Regularized Policy Optimization
Sebastian Sanokowski, Alireza Sarmadi and Majid Khadiv
Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically trained to predict returns, and accurate value predictions do not necessarily yield accurate action derivatives, potentially leading to unreliable policy updates. We propose Forward
Entropy-Regularized Policy Optimization (FERPO), an on-policy maximum
entropy reinforcement learning
algorithm that performs policy improvement using critic values without differentiating the critic with respect to actions. FERPO derives an optimal target action distribution from a policy-improvement objective regularized by
entropy and Kullback-Leibler (KL) divergence. We then fit the actor to this target by minimizing a forward-KL objective, estimated using self-normalized importance sampling (SNIS) with actions drawn from the rollout policy. By limiting the target distribution's deviation from the rollout policy, the KL regularization helps keep these importance weights well behaved. In contrast to reverse-KL objectives, which can favor a subset of the target distribution's modes, the forward-KL objective encourages coverage of multiple high-value modes and thereby promotes exploration. Experiments and ablations on MuJoCo Playground and ManiSkill show competitive performance and sample-efficiency gains. Computational
benchmarks also demonstrate faster actor updates than Relative
Entropy Pathwise Policy Optimization (REPPO).
Read the full abstract ▾
Computer Vision
HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
Tahira Kazimi, Shubhankar Borse, Munawar Hayat et al. (+2 more)
Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate
videos which adhere to laws of physics. The problem becomes even more apparent in realistic settings where multiple physical principles must work together within the same
video; for example, "a balloon floating upward while steam rises from a pot" requires buoyancy and fluid dynamics to unfold coherently and simultaneously. Yet existing methods largely ignore multi-principle interactions, focusing on a single principle per
video. We propose HiPhy (Hierarchical Physical
Alignment), a reinforcement learning framework that grounds
video generation in physical laws through a dual-level objective: locally enforcing the temporal dynamics of individual physical principles, and globally ensuring the physical and semantic coherence of the entire scene. To support multi-principle generation, we construct a 50K-
prompt dataset and introduce a
prompt benchmark MultiPhyBench, spanning a diverse range of co-occurring physical events. Our experiments show that HiPhy significantly outperforms prior methods and baselines, improving physical commonsense and semantic
alignment significantly across various
benchmarks, with the largest gains on scenes involving multiple concurrent physical principles where competing methods degrade most sharply.
Read the full abstract ▾
All authors Tahira Kazimi, Shubhankar Borse, Munawar Hayat, Fatih Porikli, Pinar Yanardag
Robotics
InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation
Zhuo Lin, Sirui Xu, Liuyu Bian et al. (+2 more)
We study test-time
evolution for
humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attempts, and retaining what it learns, without retraining. Our key insight is that a broad controller already holds much of the competence a new task needs, and that this competence becomes accessible through an interface between planning and control that is expressive enough to specify contact-rich, multi-stage interactions, yet executable and measurable enough that execution feedback can guide planning from experience. InterEvolve realizes this interface with two components. First, we develop an object-aware forward-backward (FB) behavioral foundation model, whose object residuals on a frozen body prior turn a new reward about the body or objects into loco-manipulation behavior at test time. Second, we specify tasks as reward programs: staged rewards with completion conditions and tunable constants. A large
language model (LLM)
agent revises the program structure in context, drawing on execution feedback and a skill library of verified programs, while a numerical optimizer tunes its constants. With every candidate verified across parallel simulation scenarios, the program explores new ways to induce, repurpose, and compose the controller's existing motor competence for the task at hand, and thus improves over iterations. Experiments show that human-designed rewards leave much of the FB model's loco-manipulation competence untapped, whereas the programs InterEvolve evolves release it, sometimes through novel strategies. It further produces behaviors for diverse tasks, complex scenes, and long-horizon compositions in simulation, and evolved skills run autonomously on a physical Unitree G1 from
egocentric onboard perception.
Read the full abstract ▾
All authors Zhuo Lin, Sirui Xu, Liuyu Bian, Yu-Xiong Wang, Liang-Yan Gui
Machine Learning
Cost-augmented Schrödinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
Akshay Balsubramani
The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached by learning the rates of a controlled continuous-time Markov chain, with a temporal-difference penalty that restores the cost. A state cost folds into the reference process as a Feynman-Kac tilt. The cost-augmented bridge is then a plain bridge against the tilted reference, and the penalty is unnecessary. The bridge is computed exactly by alternating two endpoint rescalings, each one sparse
matrix-exponential application; nothing is discretized in time or learned. The alternation converges at a rate set by the endpoint coupling alone. For a quadratic congestion cost on time-averaged occupancies, damped best response around the exact bridge is gradient descent on a strongly convex function, and its residual bounds its error. On a
protein-folding model, a free-energy cost lowers the expected barrier of the folding paths. On the learned approach's road network, roll-outs of the exact bridge match the target within sampling error, and on networks with millions of intersections its
memory grows linearly.
Read the full abstract ▾
Computation and Language
Hui Ren, Zihan Li, Chang Liu et al. (+2 more)
Discrete
diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional
reasoning and global constraint satisfaction. Yet they share a structural bottleneck: when decoding in parallel, each
token is sampled independently from its marginal, severing the statistical dependencies among the
tokens decoded together. Continuous
diffusion language models avoid this by denoising a shared continuous state, but their denoiser sees only that state, so nothing ties it to a valid
token configuration until it is finally decoded. To address this, we propose Hierarchical Continuous
Diffusion Language Models (HC-DLM), which couple discrete
token generation with a continuous latent trajectory in a single, principled denoising process, whose training objective is derived from a variational bound on the
token likelihood. In contrast to recent methods that attach continuous context to a self-contained discrete chain, HC-DLM makes the latent the only persistent generative state:
tokens are read out from it at every step and feed back as a scaffold for the next latent update. On structured
reasoning (Sudoku), mathematical planning (Countdown) and
language modeling (LM1B), HC-DLM improves over discrete and continuous
diffusion baselines at matched model size, in puzzle accuracy on Sudoku and Countdown and in generative perplexity on LM1B. Project page: https://hc-dlm.github.io/.
Read the full abstract ▾
All authors Hui Ren, Zihan Li, Chang Liu, Huidong Liu, Alexander Schwing
Machine Learning
The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models
Shuo Xing, Zilin Dai, Chengyuan Qian et al. (+7 more)
While Large
Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions. In this paper, we take a first step toward systematically studying mathematical understanding in LLMs, from diagnosing its distinct capabilities to leveraging these findings to improve post-training. First, we introduce the notion of Mathematical Primitive to probe structural mathematical understanding and propose \hlei{}, a novel
benchmark that evaluates mathematical
reasoning along four distinct dimensions: Discovery, Generation, Digestion, and Execution. Second, our systematic diagnosis shows that solution accuracy masks distinct capability profiles, primitives unlock substantial latent execution capacity, and Discovery is the dominant bottleneck in mathematical
reasoning. Our post-training analysis further shows that discovery-limited failures are particularly amenable to repair. Finally, building on these findings, we introduce \abs{}, a primitive-privileged self-
distillation framework that selectively transfers primitive-guided
reasoning into the student model. Extensive experiments demonstrate that \abs{} consistently improves mathematical
reasoning over baselines across model scales and challenging
benchmarks.
Read the full abstract ▾
All authors Shuo Xing, Zilin Dai, Chengyuan Qian, Fangzhou Lin, Wenjing Chen, Ping He, Pan Lu, Alvaro Velasquez, Mohit Bansal, Zhengzhong Tu
Machine Learning
Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
Cristian McGee, El Houcine Bergou and Aritra Dutta
Step-size selection remains a central challenge in large-scale neural network optimization; conservative steps slow convergence, while aggressive steps can destabilize it. We combine Zero-and-First-Order optimization~(ZFO) and propose a lightweight framework that decouples direction selection from step-size. ZFO uses a trusted first-order optimizer to determine the direction and performs zeroth-order evaluations only along this one-dimensional subspace to choose how far to move. Using the current {gradient information} and two additional objective function evaluations, ZFO instances construct a local model of the objective function along the proposed direction and select a
curvature-aware step within a bounded search interval. This yields an adaptive step-selection mechanism that costs less than a full line search. We provide theoretical guarantees to show that shared-sample evaluations produce reliable finite-difference
curvature estimates, that the induced local model selects a near-optimal step along the search interval, and that ZFO converges to a neighborhood of a stationary point. Across the evaluated settings,
language models and
datasets, ZFO frequently improves optimization and final performance relative to fixed-step first-order baselines, with the magnitude and preferred local model depending on the objective. Our code is publicly available at: https://github.com/nizswan/Zeroth-First-Order-Framework.
Read the full abstract ▾
Machine Learning
Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features
Jason X. Liu, Sebastian Ibarraran, Frank Hu et al. (+7 more)
Intrinsically disordered
protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and subcellular localization, yet their functional design remains challenging. Structure-based design methods do not readily apply to IDRs, and existing
protein language models are trained on full-length
protein sequences, thus learning a prior that is biased towards folded domains. Here, we present IDiom, an autoregressive
protein language model trained on IDiom-DB, a
dataset of 54 million predicted IDRs curated from the AlphaFold Database. IDiom generates diverse sequences that recapitulate the composition, patterning, motifs, and predicted disorder of natural IDRs. To control function-associated sequence patterns, we also introduce reinforcement learning with sparse autoencoder features (RL-SAE), a post-training method that rewards the generation of sequences that activate specified feature sets. Across eight IDR design tasks, RL-SAE sequences activate, on average, 90% of 30 targeted features, compared to 24% for activation steering. We demonstrate that RL-SAE improves the predicted subcellular localization and transcriptional activity of generated IDRs compared to steering and supervised fine-tuning, and enables features associated with distinct biological functions to be combined within individual sequences. Thus, IDiom and RL-SAE enable interpretable and composable IDR design through explicit control of function-associated sequence features. More broadly, RL-SAE could extend to other
protein design settings where interpretable features provide useful design targets. Code is available at https://github.com/rotskoff-group/idiom.
Read the full abstract ▾
All authors Jason X. Liu, Sebastian Ibarraran, Frank Hu, Soojung Yang, Xinyu A. Feng, Abigail Park, Anagha Aneesh, Lacramioara Bintu, Alexander R. Dunn, Grant M. Rotskoff
Computer Vision
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
Zhengming Yu, Junkun Yuan, Haotian Yang et al. (+8 more)
Distribution Matching
Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary
diffusion model fitted to the student's evolving distribution at extra
memory and computation cost. We introduce DMAD, Distribution Matching as
Adversarial Distillation, which recasts distribution matching as classification and learns the required log-density ratios directly. Two discriminator heads on a shared backbone distinguish real data and teacher samples from the student's, and linear losses on their logits train the student without auxiliary score fitting. We prove that at the discriminator optimum these losses recover the distribution-matching gradient underlying DMD, through the classical identity linking discriminator logits to log-density ratios. We further introduce gap-based reweighting, which adapts teacher supervision across noise levels from the real-data head's empirical logit gap between real and teacher samples. DMAD reaches a Fréchet Inception Distance (FID) of 1.04 with one-step generation on ImageNet-64x64, 14.47 with four-step SDXL on COCO-10K, and a VBench total score of 85.15 with four-step Wan2.1-T2V-14B, the best values among the compared few-step methods and the multi-step teachers. On MiniMax-H3-33B, our four-step student achieves overall human preference rates of 79.1% over DMD2 and 84.6% over rCM for joint audio-
video generation, excluding ties. Our code, models and demos are available at https://yzmblog.github.io/projects/DMAD.
Read the full abstract ▾
All authors Zhengming Yu, Junkun Yuan, Haotian Yang, Gordon Guocheng Qian, Yizhi Wang, Angtian Wang, Yiding Yang, Bo Liu, Xin Li, Wenping Wang, Chongyang Ma
Systems and Control
Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
Alexey Peregudin and Ngoc Tuan Dinh
On broad classes of linear systems, the shortest experiments are almost as good as the best possible ones. For $n$ states and $m$ inputs, the shortest input sequences that support robust data-driven stabilization of every controllable plant have $mn+1$ steps with exact states and $m(n+1)$ with noisy states. We show that, when the spectral radius is bounded and the spectrum is well separated near the unit circle, these sequences tolerate a fixed fraction of the error level achievable by any experiment, even one designed with full plant knowledge and allowed to use any finite duration. This constant-factor comparison can fail for slowly actuated systems. For $A=I+hG$ with controllability depth $\nu\ge2$, short experiments lose a factor of order $h^{\nu-1}$, and duration of order $1/h$ is both necessary and sufficient to recover a fixed fraction of the optimal tolerance.
Read the full abstract ▾