Curated academic papers that inform our research directions.
Note: These are external publications from arXiv, not SparseTech publications. We share them as context for the mathematical foundations underlying our work.
Hierarchical Denoising For Multi-Step Visual Reasoning
Zezhong Qian, Xiaowei Chi, Chak-Wing Mak +9 more
Published: July 16, 2026
cs.CV
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both…
Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models
Patrik Wolf, Thomas Kleine Buening, Andreas Krause +1 more
Published: July 16, 2026
cs.CL
In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In…
RoboTTT: Context Scaling for Robot Policies
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng +8 more
Published: July 16, 2026
cs.ROcs.AIcs.LG
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference…
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
Yushi Huang, Xiangxin Zhou, Jun Zhang +2 more
Published: July 16, 2026
cs.CVcs.LG
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular,…
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Yasheng Sun, Zezi Zeng, Yifan Yang +4 more
Published: July 16, 2026
cs.CLcs.AI
Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a…
Online Neural Space Time Memory for Dynamic Novel View Synthesis
Baback Elmieh, Lynn Tsai, Zeman Li +8 more
Published: July 16, 2026
cs.CVcs.GRcs.LG
Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism, standard models…
Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography
Guang Yang, Wentian Xu, Siyu Wang +3 more
Published: July 16, 2026
cs.CV
Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptors or densely…
Pretraining Data Can Be Poisoned through Computational Propaganda
Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith +2 more
Published: July 16, 2026
cs.AIcs.CL
Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored…
SceneBind: Binding What and Where Across Vision, Audio and Language
Mingfei Chen, Zijun Cui, Ruoke Zhang +2 more
Published: July 16, 2026
cs.CVcs.AIcs.MM
We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind…
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
Paul Kassianik, Blaine Nelson, Yaron Singer
Published: July 16, 2026
cs.CRcs.AI
Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool call, telemetry…
The Power of the Score Sequence of a Tournament
Prantar Ghosh, Sahil Kuchlous, Shravan Mehra +1 more
Published: July 16, 2026
cs.DS
What problems can one solve on a tournament if only its score sequence is known?
Tournaments are oriented complete graphs that form an extensively-studied class of directed graphs (digraphs), both from combinatorial and algorithmic perspectives. Over the years, researchers have identified multiple classical digraph…
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier
Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca +3 more
Published: July 16, 2026
cs.LGcs.CE
The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models that aim to predict…
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Yuyao Zhang, Junjie Gao, Zhengxian Wu +11 more
Published: July 16, 2026
cs.AIcs.IR
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can…
Analytic finite-rank corrections for singularly weighted estimates in a computer-assisted proof of 3D Euler singularity
Jiajie Chen, Thomas Y. Hou
Published: July 16, 2026
math.APmath.NA
Computer-assisted proofs of self-similar singularity formation for fluid equations often rely on numerically constructed approximate profiles. One effective approach to establishing stability of perturbations around a numerically constructed profile is to perform weighted energy estimates with singular weights near the…
HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning
Pengcheng Zhou, Xuanyu Liu, Yanchen Yin +4 more
Published: July 16, 2026
cs.CV
Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically investigate this…
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Qiwei Li, Jorge Ortiz
Published: July 16, 2026
cs.AIcs.HC
Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for…
Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search
Debayan Mukhopadhyay, Utshab Kumar Ghosh, Shubham Chatterjee
Published: July 16, 2026
cs.IRcs.CL
Retrieval systems are trained and evaluated on a static idea of usefulness: hand a document and a question to a reader model, see whether the answer improves, and score the document accordingly. The idea holds up when a document is read on its own. It breaks when a language model works as a search agent, issuing…
AutoSynthesis: An agentic system for automated meta-analysis
Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano +2 more
Published: July 16, 2026
cs.AI
Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a…
ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho +3 more
Published: July 16, 2026
cs.CV
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when…
Mutable Low-Rank Sketches for Retrain-Free Recommendation
Hector J. Garcia, Nick Clayton
Published: July 16, 2026
cs.LG
A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once,…
Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA
Sushant Gautam, Vajira Thambawita, Michael A. Riegler +2 more
Published: July 16, 2026
cs.CLcs.CV
Healthcare multimodal AI must combine visual and textual evidence while remaining reliable and interpretable. Using MediaEval Medico 2025 as a retrospective GI endoscopy case study, we analyze design choices across nine documented systems for question answering and explanation quality. Parameter-efficient adaptation of…
TikStance: A Multimodal and Hierarchical Dataset for Multi-target Stance Analysis in TikTok Political Conversations
Yazhi Zhang, Fuqiang Niu, Bowen Zhang
Published: July 16, 2026
cs.CL
Political discourse has increasingly moved to short-video platforms, yet computational analysis of such content remains constrained by the scarcity of datasets that jointly preserve audiovisual information and hierarchical conversations. Here we present TikStance, a multimodal and context-aware dataset comprising 161…
Language Identification via Compositional Data Analysis: A Linear-Time Classifier Based on Log-Ratio Geometry
Paul-Andrei Pogăcean, Sanda-Maria Avram
Published: July 16, 2026
cs.CL
Language identification is commonly addressed using either neural architectures or statistical n-gram models. Neural approaches typically require substantial computational resources, whereas classical frequency-based methods offer efficient linear-time performance, but rely on distance metrics that are not always…
In-Place Tokenizer Expansion for Pre-trained LLMs
Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera +7 more
Published: July 16, 2026
cs.CLcs.AIcs.LG
A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy consumption for users…