Information Theory
Systematic Codes Correcting Two Deletions with Three Redundant Symbols over Large Alphabets
Valery Grishin and Aryeh Lev Zabokritskiy
We construct systematic $q$-ary codes correcting two deletions with three redundant symbols over
polynomial-size alphabets. For every information length $n\ge2$, our first construction has length $n+3$ over an alphabet of size $q=2^s<2^{32}n^7$ for some integer $s$, with
polynomial-time encoding and decoding. A cardinality bound of Liu and Xing implies that three redundant symbols are necessary, so the construction is optimal in this measure. We also establish the existence of systematic codes with the same redundancy over alphabets of size $O(n^4)$, leaving efficient encoding and decoding at that alphabet scale open. For a single burst of at most two adjacent deletions, we give a
polynomial-time systematic construction with three redundant symbols over a power-of-two alphabet of size $q<(n+2)^4$. A converse bound for adjacent deletions shows that three redundant symbols are again optimal for $n\ge2$.
Read the full abstract ▾
Cryptography and Security
Robustness of Local Energy Markets to Cyberattacks: Case Study of False Data Injection
Mehran Moradi, Reza Zamani, Phil Aupke et al. (+2 more)
Market clearing in community-based local energy
markets relies on power demand and PV forecasts, making it vulnerable to coordinated false data injection (FDI) attacks. This paper proposes a bilevel optimization framework to identify worst-case bus-level FDI against interconnected multi-community electricity
markets within a distribution network. The upper level attacker maximizes physical impact, measured by cumulative voltage deviation, while accounting for detectability. The lower level re-clears the interconnected multi-community
markets subject to operational and network constraints. The bilevel model is reformulated as a single-level mixed-integer program through Karush-Kuhn-Tucker conditions and solved using the epsilon constraint method to characterize the trade-off between physical impact and detectability. Case studies on the IEEE 33-bus system with three communities show that even bounded, system-level zero-sum attacks can reshape local trading, reduce voltage security margins, and produce asymmetric community-level
market outcomes. The results further show that vulnerability depends strongly on the spatiotemporal placement of falsified data rather than on uniform spreading across buses and time periods.
Read the full abstract ▾
All authors Mehran Moradi, Reza Zamani, Phil Aupke, Andreas Theocharis, Andreas Kassler
Software Engineering
Xijia Tao, Ziru Liu, Shansan Gong et al. (+7 more)
Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked
diffusion language models divide these responsibilities across four editing interfaces: whole-file rewriting, search-and-replace, locate-then-infill, and
token-level editing. Experiments on CanItEdit reveal a composition gap:
diffusion models can generate coordinated changes when the correct edit locations are supplied, but much of this capability is lost when those locations must be predicted. Access to the intact original code helps the model fill multiple edit regions, yet does not resolve the difficulty of selecting those regions. By varying the editable regions while holding the generation model and decoding procedure fixed, we identify two distinct requirements for successful editing: covering every required change and placing precise boundaries around it. Missing a required region prevents the corresponding change, while widening regions to ensure coverage can sharply reduce success by requiring unchanged code to be regenerated. A sentence-level Wiki editing probe shows the same qualitative gap between supplied and predicted locations beyond code. These findings show why strong infilling capability alone does not ensure reliable editing: the interface must expose all required changes while limiting regeneration of unchanged code.
Read the full abstract ▾
All authors Xijia Tao, Ziru Liu, Shansan Gong, Jiacheng Ye, Kecheng Chen, Zirui Wu, Lin Zheng, Xinyu Fu, Rui Liu, Lingpeng Kong
Computation and Language
Framing the Narrative: Ideological Mimicry in Large Language Models
Olivia Macmillan-Scott, Michael Jacobs, Nils Metternich et al. (+1 more)
Large
language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's stance as a relatively stable property. Real users, however, communicate political signals through their terminology, assumptions, and personal context. We investigate whether such signals produce ideological mimicry: systematic shifts in the political stance expressed by an LLM toward the position conveyed by the interaction. If LLMs adapt their responses to these signals, they risk creating personalised political information environments in which users with opposing views receive systematically different accounts of the same issue, potentially reinforcing existing divisions. We build the Poli-SHIFT
dataset and evaluation framework and assess seven open-weight LLMs across ten contentious political topics in the United States, United Kingdom, and Australia, systematically manipulating contested terminology, politically valenced premises, and user information, and eliciting responses in both multiple-choice and open-text formats. Across models, we find robust evidence that
prompt framing shapes the political stance of LLM outputs. Changing terminology alone reverses which side of an issue a model supports in 16.9% of matched comparisons. Stated political ideology also systematically shifts responses toward the user's position. These findings show that political stance is not a fixed property of LLMs; the views expressed are conditional on the interaction with the user. As LLMs become increasingly personalised sources of information, such interaction-dependent adaptation could contribute to political information environments that reinforce users' existing perspectives.
Read the full abstract ▾
All authors Olivia Macmillan-Scott, Michael Jacobs, Nils Metternich, Mirco Musolesi
Cryptography and Security
CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition
Zhiyi Mou, Yao Lu, Wangze Ni et al. (+6 more)
Text-to-image (T2I) models have substantially improved in
language understanding, in-image text rendering, and visual composition, while their safety mechanisms do not always keep pace with these capabilities. This creates a cross-modal attack surface in which harmful semantics can remain inconspicuous in a serialized
prompt yet emerge through image-level composition. We propose CollageAttack, an automated single-
prompt black-box jailbreak that shifts semantic assembly into the image plane by combining context-relevant scenes, scene-grounded textual carriers, and spatially distributed text fragments. Experiments across multiple open-weight and commercial T2I models show that CollageAttack achieves attack success rates of up to 86.0%, outperforming the strongest baseline on the same model by 18.5 percentage points, while consistently producing more harmful outputs and preserving the source intent. We further find that distributed textual fragments can reconstruct the intended semantics after generation, with visual composition producing stronger communicative impact than text alone. These results reveal a cross-modal safety gap in which harmful meaning emerges from the composition of individually less explicit elements.
Read the full abstract ▾
All authors Zhiyi Mou, Yao Lu, Wangze Ni, Di Hong, Dakun Shen, Haoyang Li, Chen Jason Zhang, Alexander Zhou, Kui Ren
Cryptography and Security
Multilayer Forensic Tampering Detection
Titouan Millet, Thomas Valade, François Gonnet et al. (+1 more)
With the proliferation of free online editing tools, altering or forging pdf documents has become trivially easy, often leaving no visual traces on screen. This paper introduces a two- stage forensic pipeline. An initial security-gating layer validates format compliance and flags embedded malicious payloads and a forensic engine that inspects internal objects across meta- data, visual overlays, and dual-source OCR consistency, etc... A weighted scoring engine aggregates these forensic indicators into an interpretable risk score is proposed. The approach was validated on real medical work-stoppage certificates.
Read the full abstract ▾
All authors Titouan Millet, Thomas Valade, François Gonnet, Mounira Msahli
Cryptography and Security
Forensic-Aware Continual Adaptation for Image Forgery Localization
Chenqi Kong, Song Xia, Anwei Luo et al. (+3 more)
The rapid
evolution of image manipulation techniques has raised growing public security concerns. Existing Image Forgery Localization (IFL) methods can accurately localize manipulated regions but are often unable to adapt to newly emerging forgeries. In real-world forensic scenarios, data typically arrive sequentially, yet continual model adaptation remains largely unexplored in IFL. To bridge this gap, we introduce the first continual learning framework for IFL and establish a comprehensive
benchmark under two realistic data-
evolution protocols: cross-
dataset and cross-content continual learning. Evaluations of representative state-of-the-art IFL and continual learning methods reveal substantial performance degradation, highlighting two key challenges: (1) adaptively capturing intrinsic forensic traces from incoming data across unseen domains, and (2) preserving previously acquired forensic knowledge during sequential adaptation. To address these challenges, we propose a forensic-aware continual adaptation framework. First, a forensic trace mining module employs Spatial Mixture-of-Forensic-Experts (SMoFE) to dynamically route complementary forensic cues across spatial locations, together with Forensic Evidence-Guided Dense Prompting (FEGDP) to transform low-level forensic traces into structured localization evidence for SAM. Second, Fisher-weighted LoRA Gradient (FLAG) surgery identifies old-task-sensitive adaptation directions and suppresses conflicting updates, mitigating catastrophic forgetting while preserving plasticity for emerging forgery domains. Extensive experiments demonstrate state-of-the-art performance in both pixel-level forgery localization and image-level forgery detection across diverse continual learning scenarios.
Read the full abstract ▾
All authors Chenqi Kong, Song Xia, Anwei Luo, Peisong He, Alex C. Kot, Yuming Fang
Cryptography and Security
SURE: Framework for Safety to Construct Trustworthy AI
Soeun Han, Jisoo Lee, Jeongyong Shim et al. (+2 more)
Warning: This paper contains harmful and offensive text. Recently, large
language models such as GPT-4, and Claude have revolutionized tasks in various domains. As the use of these large
language models increases, people are increasingly concerned about AI safety and demand that large
language models behave responsibly and safely. As a result, there has been growing global interest in developing methods to ensure AI safety. However, the detailed criteria for AI safety may vary depending on the country, culture, and policies of the company you serve. In this study, we propose SURE (A Safe and Unified AI Framework foR Everyone), which is designed as a framework for customizing the attributes of AI safety and ensuring the defined AI safety. Within SURE, we establish taxonomies for
adversarial prompts that could threaten AI safety and construct
prompts based on the taxonomies. We then define templates for desirable AI responses to these
prompts and design an absolute safety scoring scheme. Finally, we conduct AI
alignment using the
datasets to gradually ensure AI safety. The effectiveness of SURE is demonstrated through experiments with various base models.
Read the full abstract ▾
All authors Soeun Han, Jisoo Lee, Jeongyong Shim, Eunkyeong Lee, Eunmi Kim
Cryptography and Security
ContractWarden: Kernel-Enforced Damage Boundaries for AI Agents via Human-Authorized Contracts
Dongxu Cui, Zhichao Gu, Ping Zheng et al. (+3 more)
Large
language model
agents can execute commands, create subprocesses, and directly access files and networks, allowing
prompt injection or planning errors to become operating-system side effects. We present ContractWarden, a Linux reference monitor that enforces a human-authorized damage boundary without trusting the
agent or its policy suggestions. A model may propose a tri-state asset contract - allow, deny, or no_egress - but a human makes the final choice. An execution gate binds the contract to a concrete task before untrusted code runs. An extended Berkeley Packet Filter (eBPF) Linux Security Modules (LSM) data plane then enforces file and network decisions and monotonically propagates no_egress through processes, regular files, pipes, FIFOs, and supported Unix-domain sockets. All 570 runs across 19 security tests satisfy predefined return-value and side-effect criteria. On three co-located file-I/O workloads, median overhead is 11.96-12.89% in a Linux 6.15 virtual machine and 35.79-61.54% on a Linux 6.15 physical platform, lower than the evaluated frozen ActPlane baseline. The results demonstrate deterministic kernel enforcement for declared assets, supported paths, and controlled object lifecycles.
Read the full abstract ▾
All authors Dongxu Cui, Zhichao Gu, Ping Zheng, Wenshuai Xi, Simeng Han, Yong Liao
Cryptography and Security
ModalFidelity: Routing Modalities for Deepfake Detection on a Budget
Oguzhan Baser, Kaan Kale, Sriram Vishwanath et al. (+1 more)
Deepfakes no longer need to fake a whole
video. Generators that read the transcript now alter only the few seconds in which a
video's meaning turns, so a forgery hides in a small, unknown fraction of the
video. Yet detectors still read every one-second window of both the audio and image streams, spending nearly all of their compute where nothing was altered. We observe that deciding where to look is far cheaper than looking. We present ModalFidelity, a lightweight router that previews each window and decides, before any forensic detector runs, which stream is worth reading, under a hard compute budget it can never exceed. On AV-Deepfake1M, reading at most a fifth of the windows, it is more accurate than gating after the detectors at 15.9x less compute, and retains over 96% of the accuracy of an oracle that knows where every forgery lies.
Read the full abstract ▾
All authors Oguzhan Baser, Kaan Kale, Sriram Vishwanath, Sandeep Chinchali
Cryptography and Security
Agent-Warden: eBPF-Based Kernel-Native Process-File Provenance Tracking for LLM Agents
Dongxu Cui, Zhichao Gu, Ping Zheng et al. (+2 more)
LLM
agents execute dynamically generated process and file operations that are often invisible to application-layer tracing. We present
Agent-Warden, an extended Berkeley Packet Filter (eBPF)-based provenance monitor for tracking task and regular-file states across process creation, file access, and process termination.
Agent-Warden provides two interchangeable state backends: a PID-keyed hash-map backend for compatible kernels lacking BPF local-storage support and a task/inode-local-storage backend that couples state reclamation to kernel-object lifetimes. The system emits incremental causal edges to user space for asynchronous graph reconstruction and applies conservative exit-triggered causal aggregation to preserve causal context for short-lived proxy tasks. In a controlled file-mediated propagation scenario,
Agent-Warden reconstructed a cross-process causal chain that was absent from the application-layer trace. On x86-64 and ARM64 bare-metal hosts, the evaluated workloads showed 0.2-3.5% end-to-end overhead and 0.6-3.7% additional system CPU time. These results indicate that the prototype provides kernel-level visibility with the measured overheads in the evaluated settings.
Read the full abstract ▾
All authors Dongxu Cui, Zhichao Gu, Ping Zheng, Simeng Han, Yong Liao
Information Theory
Approximate Uniformity in Finite Convolution Models
Nilava Metya and Satyaki Mukherjee
The problem of the uniform law being a sum of two independent distributions has been well studied. Here, we study the approximation of the uniform law to a sum of two distributions with fixed support, under the following discrepancies: the Manhattan distance, the Euclidean distance, the forward Kullback–Leibler divergence and the Wasserstein-one distance based on the line metric. The problem of membership of the uniform law in this model has been well studied. Explicit results are obtained in two models, one where one of the distributions is a Bernoulli and the other when both distributions have the same support, including one
conjecture. Finally, we show an application of our reconstruction method to a recent
conjecture about the coding capacity of an additive noise channel.
Read the full abstract ▾
Programming Languages
A Calculus for Units of Measure with Conversion
Eric Allen
Programs that compute with physical quantities often need to convert between units of measurement, and as the Mars
Climate Orbiter showed, these conversions can be a rich source of errors. Meanwhile, typed unit calculi, our most rigorous formalisms for checking physical units in a program, have excluded unit conversions. Through this exclusion, they have established a powerful property: well-typed programs are invariant under rescaling (no program can depend on how big a meter is). But losing the ability to convert between units is a significant cost. In contrast, practical
languages provide conversion but no invariance
theorem. We present $\Lambda_S$, a typed lambda calculus with conversion, quantification over units and dimensions, and vectors and linear maps with per-component units, and we determine exactly how much invariance survives conversion. For terms without unit constants we prove two abstraction
theorems: (i) a convert-free term is invariant under every rescaling; (ii) a term with conversions is invariant under every rescaling that scales all units of one dimension by the same factor. The condition in (ii) cannot be weakened: under any other rescaling, some conversion of a nonzero value is not invariant. For first-order programs, a verified decision procedure returns one of three verdicts: it certifies that no error in the declared conversion factors can change the program's answer, names the accumulated ratio through which such an error would scale it, or declines. A verified checker decides whether unit declarations are consistent and determine every conversion factor, and extracts each factor exactly. We also prove adequacy, erasure, and the $n$-variable Pi
theorem of dimensional analysis with conversion. Every
theorem is mechanized in Lean 4, and the evaluator compiles to a native binary.
Read the full abstract ▾
Cryptography and Security
Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse
Keifer Lee
A Technical Report: Operating a large
language model (LLM) as a service requires more than inference infrastructure: the provider must also defend against
adversarial interactions that seek to exploit the service, including jailbreaking for harmful use, sophisticated denial of service, and
distillation attacks. We study this problem at the inference layer, using a hypothetical frontier lab, Five Elements Inc., as a running example. Because no public labelled
dataset of
adversarial LLM usage exists, we introduce a structural causal model (SCM) that generates a realistically grounded, labelled
dataset of user-sessions, with coordinated multi-account campaigns, platform feedback, and three tiers of label observability. On this
dataset we train a practical gradient-boosted detector that classifies each user-session as benign or malicious and, if malicious, by attack type. Against oracle labels the detector very nearly solves the binary task (AUPRC $0.993$), yet against the operational labels a real Trust & Safety team would hold, the same model scores an AUPRC of only $0.313$: the detector is more accurate than the labels used to evaluate it. For attack-type attribution, a naive argmax is dominated by the $98\%$ benign prior (macro-F1 $0.295$), whereas a simple thresholded decision engine raises macro-F1 to $0.489$ without sacrificing accuracy. The
dataset is publicly released.
Read the full abstract ▾
Computer Vision
Point2Part: Unified 3D Partitioning from Point Prompts
Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma et al. (+3 more)
Existing 3D part decomposition methods do not necessarily partition the original shape into non-overlapping parts that collectively cover the entire shape, allowing overlaps or gaps that hinder downstream part-level applications. We instead formulate part decomposition as a joint partitioning of the entire shape, where the predicted parts are non-overlapping and jointly recover the entire shape. Our key insight is that part decomposition should consider all desired parts jointly, rather than modeling each part independently. To this end, we develop a promptable model for 3D part decomposition from images or meshes. Users can specify desired parts through 3D point
prompts for controllable decomposition. Given one point
prompt per desired part, our model produces the corresponding parts as a complete partition of the entire shape. We build on a pretrained 3D generation model and first obtain a shape latent from either an input image or mesh. We then introduce a
prompt encoder that maps each 3D point
prompt to a part
token while attending to the shape latent. To decode the desired parts, we propose a novel part decoder jointly scoring the entire shape against all part
tokens in a coarse-to-fine manner, assigning every position within the shape volume to exactly one part. We perform part decomposition in this shared shape latent space, enabling a unified model for image-to-part generation, mesh-to-part generation, and part
segmentation. Our method outperforms existing works on all part-quality metrics across all three tasks, and improves compatibility among parts by an order of magnitude over previous SOTA methods. Code and models will be released.
Read the full abstract ▾
All authors Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma, Nicolas Ugrinovic, Takaaki Shiratori, Kris Kitani
Robotics
Skill-Space Shooting for Autonomous Robot Policy Improvement
Zihang Rui, Renhao Wang, Haoxu Huang et al. (+1 more)
Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this improvement to scale across tasks, it must make effective use of experience without requiring human demonstration of each correction. Recent agentic systems offer a way to reduce this reliance on human effort by using foundation models to autonomously compose learned behaviors to complete tasks. Yet completing tasks this way does not itself teach a task policy to overcome its own failures; that requires turning these behaviors into learnable corrections for the policy. Our insight is that many such corrections are familiar short behaviors, or skills: they recur across tasks and describe actions that foundation models can reason about from a scene. We introduce skill-space shooting, which uses foundation model guidance to explore corrections through these reusable skills and turn successful trials into policy improvement. Real-world experiments show repeated improvement in policies acting autonomously, while skills can also be shared to reduce the teaching needed to improve on new tasks. By making reusable skills a source of corrective supervision, skill-space shooting enables scalable and generalizable policy improvement within and across tasks. Additional results and
videos at https://skill-space-shooting.github.io.
Read the full abstract ▾
All authors Zihang Rui, Renhao Wang, Haoxu Huang, Yang Gao
Computer Vision
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
Jaewoo Jung, Hyeonseo Yu, Honggyu An et al. (+10 more)
Reasoning about the 3D world from multi-view images remains a fundamental challenge for
Multimodal Large
Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evidence across viewpoints into a coherent 3D understanding. A growing body of work attempts to close this gap by injecting 3D awareness into MLLMs, either by boosting fine-grained pixel-level cross-view correspondence or by fusing features from 3D geometry foundation models, yet a substantial gap to human
reasoning persists. In this work, we revisit human spatial
reasoning, which suggests that rather than relying on fine-grained geometry cues, humans roughly identify common objects across views, infer the relative geometry between viewpoints, and assemble a coarse 3D layout of the scene. Inspired by this process, we introduce Imagine3D-LLM, an MLLM that learns to assemble a similar compact 3D representation of the scene and conditions its answer on this representation. Concretely, we append a small set of learnable summary
tokens after the image
tokens, decode them into a compact 3D Gaussian Splatting representation supervised by a photometric reconstruction loss, and train jointly with the standard next-
token prediction objective. Notably, although only the summary
tokens receive direct reconstruction supervision, this objective also induces stronger cross-frame correspondence within the LLM's underlying image features, suggesting that learning to reconstruct propagates 3D-aware signals throughout the model. As a result, Imagine3D-LLM consistently outperforms prior approaches across multiple spatial
reasoning and 3D understanding
benchmarks, suggesting that imagining the scene can be more effective than being told its pixel-wise geometry.
Read the full abstract ▾
All authors Jaewoo Jung, Hyeonseo Yu, Honggyu An, Jisang Han, Mungyeom Kim, Minkyeong Jeon, Heeseong Shin, Wonjun Moon, Federico Tombari, Daniel Barath, Marc Pollefeys, Seungryong Kim, Sunghwan Hong
Machine Learning
Breakdown of Local Denoising as Semantic Speciation
Guangkuo Liu, Mert Okyay, Yifan F. Zhang et al. (+3 more)
The dynamics of generative models exhibit two apparently distinct temporal windows: a speciation window, in which a sample commits to a semantic class, and a nonlocality window, in which local context windows become insufficient for generation. Motivated by evidence of their near-concurrence in a variety of frontier models, we investigate their relationship through the spatial distribution of semantic information. Under a "common cause" hypothesis, we prove that the nonlocality window must lie in the speciation window. This hypothesis postulates that semantic labels explain a fraction of the correlations between distant
tokens, a condition that is natural for many real
datasets. We further give conditions under which both windows shrink to a single limiting time as system size grows, defining a "phase transition", and verify this behavior analytically in Gaussian mixtures. Together, these results identify conditions under which semantic information explains the concurrence of speciation and nonlocality, connecting two complementary perspectives on the emergence of semantic structure in generative modeling.
Read the full abstract ▾
All authors Guangkuo Liu, Mert Okyay, Yifan F. Zhang, Fangjun Hu, Rahul Nandkishore, Xun Gao
Robotics
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Minxing Li, Minghao Han, Weizhi Zhao et al. (+10 more)
We study robotic in-context learning (ICL), an emerging paradigm that enables
robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself remains under-defined: a visual demonstration simultaneously conveys action trajectories, object semantics, manipulation affordances, spatial relations, and task goals, making it unclear what information the
robot is actually expected to follow. In this work, we first provide a clear problem definition of
robot ICL that explicitly defines its learning target and resolves this fundamental
prompt ambiguity. Building on this definition, we develop a minimalist and reproducible ICL framework (SimpleICL) with a visual
prompt encoder and a low-cost data collection protocol. Without massive pre-training or specialized data infrastructure, our framework achieves strong performance in both simulation and real-world environments. Extensive experiments further reveal several key properties of
robot ICL, including semantic discrimination and task-relevant disentanglement. We will fully open-source our data and training pipeline to facilitate systematic and reproducible research on
robot ICL. The project page can be found at https://simpleicl.github.io/simpleicl.
Read the full abstract ▾
All authors Minxing Li, Minghao Han, Weizhi Zhao, Hanwen Wang, Xiangshuo Liu, Shuyao Shang, Jingxiang Zhou, Mingchao Sun, Hongyu Pan, Mu Xu, Yu Liu, Lue Fan, Zhaoxiang Zhang
Robotics
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
Zihan Wang, Zhen Wu, Pieter Abbeel et al. (+6 more)
Teaching
humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist
robots. However, collecting diverse, high-quality interaction
videos, such as clips that clearly show a person's full body and unoccluded interactions with objects, poses a practical barrier to scaling this approach. We propose PRISM, a real-to-sim-to-real framework that overcomes this limitation by amplifying a handful of real
videos into a large, diverse training set. PRISM first generates hundreds of diverse "counterfactual" human-object interaction
videos via
video-to-
video (V2V) generation from a few exemplar real
videos. Our contact-anchored real-to-sim pipeline then reconstructs both human and object motions, retargeting this imperfect
video data into physically plausible trajectories. The intra-class variability across these counterfactual
videos lets us train a single policy that generalizes to unseen objects within each category. We demonstrate the full pipeline by deploying this policy on a real
robot without any real-world fine-tuning. Using only onboard depth observations, our
humanoid picks up, carries, and drops objects, including boxes, barrels, bins, and balls, across novel instances, sizes, and initial configurations.
Read the full abstract ▾
All authors Zihan Wang, Zhen Wu, Pieter Abbeel, Rocky Duan, Jitendra Malik, Carmelo Sferrazza, C. Karen Liu, Guanya Shi, Angjoo Kanazawa
Computer Vision
Xin Lin, Zhifei Zhang, Yuqian Zhou et al. (+4 more)
Pixel
diffusion models generate RGB images directly, avoiding the bottleneck of an autoencoder, yet their outputs still systematically underrepresent fine-scale natural-image statistics. We show that
adversarial learning provides an effective post-training correction for this deficiency. Starting from a pretrained model, we retain its original
diffusion or flow-matching objective and add an
adversarial loss to the predicted output at non-high-noise timesteps, leaving the model architecture and sampling procedure unchanged. To our knowledge, this is the first systematic study of
adversarial post-training for pixel
diffusion. Across two pixel backbones, the method jointly improves distribution fidelity, coverage,
prompt alignment, and perceptual quality. We further investigate why it works. Frequency-band and power-law analyses show that the original models systematically underproduce natural-image high-frequency content, while
adversarial post-training restores this missing spectral power. In contrast, perceptual loss also increases high-frequency content but sacrifices distribution fidelity and
prompt alignment. Nearest-neighbor, recall, and matched no-GAN SFT controls further rule out memorization, mode dropping, and additional optimization as simple explanations. Finally, we examine the boundary of this effect. Under the tested latent
diffusion configurations, the same procedure does not produce comparable joint gains and adds almost no decoded high-frequency power. These results identify direct output access to the image statistics being corrected as a key factor governing when
adversarial post-training succeeds.
Read the full abstract ▾
All authors Xin Lin, Zhifei Zhang, Yuqian Zhou, Haitian Zheng, Zhe Lin, Ming-Hsuan Yang, Truong Nguyen
Computation and Language
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Bingchen Yao, Haobo Xu, Haokun Lin et al. (+6 more)
Linear
attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial
memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dimensions: temporally, errors in long-lived
memory can persist across many decoding steps; spatially, errors in different key rows affect model outputs differently, while state magnitudes vary substantially along both rows and columns. Motivated by these observations, we propose STEPQuant, a spatial-temporal post-training quantization framework for Delta-rule recurrent states. STEPQuant allocates precision according to error magnitude and
memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error. Experiments on Qwen3.8-27B and Kimi-Linear-48B-A3B-Instruct across both long- and short-generation
benchmarks show that STEPQuant closely matches FP32-state accuracy under a nominal 6-bit budget and outperforms uniform INT8 in its 4-bit configuration. Integrated into SGLang with optimized GPU kernels, 6-bit STEPQuant achieves over 5x recurrent-state compression and reduces total serving
memory by up to 68.7%. Our code is available at https://github.com/Dreamer-Toby/STEPQuant.
Read the full abstract ▾
All authors Bingchen Yao, Haobo Xu, Haokun Lin, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Zhenan Sun, Ying Wei
Machine Learning
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
Yi Pan, Haocheng Xi, Kan Zhu et al. (+10 more)
Recent LLMs increasingly adopt hybrid designs that replace standard
attention with linear
attention, such as Gated DeltaNet (GDN) and Kimi Delta
Attention (KDA). Although they compress the context into a fixed-size recurrent state and substantially reduce the cost of long-context processing, repeatedly reading and updating that state remains a major inference bottleneck. Quantization offers a natural way to reduce this cost, but can significantly degrade model quality, due to the accumulation of rounding errors and the presence of outlier rows and columns in the state. To address these challenges, we propose LeapQuant, a training-free method that achieves near-lossless performance under 8-bit recurrent-state quantization. First, to mitigate error accumulation, we propose per-window quantization, which leaps over a window of
tokens and quantizes the state only once at its end. Within a window, outputs are computed from the fixed low-bit state together with high-precision buffered updates. Second, to reduce the error introduced by each quantization, LeapQuant retains the state's largest outliers as a few high-precision Compensator
Tokens, which share the update path of real
tokens. We then smooth the remaining residual before quantization to further reduce the error. Comprehensive experiments across the Qwen, Kimi, and GLM model families show that LeapQuant substantially reduces
memory and compute costs during inference. With accuracy comparable to the FP32 baseline, it achieves average speedups of 2.05–3.70$\times$ at the kernel level and 1.47$\times$ for end-to-end inference on NVIDIA B200, RTX PRO 6000, and RTX 5090 GPUs.
Read the full abstract ▾
All authors Yi Pan, Haocheng Xi, Kan Zhu, Xingyang Li, Yibo Wu, Mayank Mishra, Hongtao Zhang, William X.Zheng, Baris Kasikci, Song Han, Kurt Keutzer, Rishabh Iyer, Ion Stoica
Computer Vision
Cropland PAtteRNS: Parallel Dimensional Attention Networks and Attention to Dataset Disparity for Crop Segmentation in Satellite Imagery Time Series Data
Joseph Metcalfe, Sara Sharifzadeh and Fabio Caraffini
The landscape of satellite imagery time series
datasets and boundary-pushing architectures for cropland
segmentation has never been richer. However, in this gold rush, important truths are being missed on both fronts, as a drive for the most novel concepts or the largest
datasets pushes finer details to the side. In this paper, we present our hybrid
transformer-convolutional model, Cropland Parallel
Attention and Refinement Network for
Segmentation (PAtteRNS), the first model to use self-
attention mechanisms separately for each of the temporal, spectral, and spatial aspects of Sentinel-2 multispectral SITS data. To achieve fully-factorised
attention in our proposed model, we introduce a novel parallel
transformer architecture which significantly reduces the computational complexity of triple-factorised self-
attention. We validate our architecture with an in-depth ablation study, and analyse the performance of our model against state-of-the-art crop
segmentation models on multiple tile-size variants of the popular PASTIS and MTLCC
datasets. Our findings show our model to outperform all others in the task of crop class
segmentation, verified across multiple important
segmentation metrics, with especially strong performance against compared models seen in the often under-reported parcel delineation quality, for which we use the Boundary IoU metric. We also find that flawed class groupings within
datasets can have a significant negative impact on model performance, and report that alternate tile-size variants of crop
segmentation datasets produce results incomparable to one-another, invalidating fair comparison between model performance when trained on different tile-sizes. Based on these findings, we suggest further work is required to standardise best practices when constructing SITS crop
segmentation datasets, and to enable future dynamic-tile-sizing for ideal model performance.
Read the full abstract ▾
Robotics
Rho: A Foundation for Efficiently Adaptable VLA Models
Rho Team: Simran Bagaria, Daphne Chen, Dean Fortier et al. (+10 more)
General-purpose physical AI models must combine broad visual and linguistic capabilities with precise control across
robot embodiments and efficient adaptation to downstream tasks. We introduce Rho, a family of open-weights VLA models for bimanual manipulation designed for data-light task adaptation on 3 embodiments representative of dual-arm
robots across research labs and the industry – YAM Box, UR AI Trainer, and FR3 Duo. We systematically ablate Rho's action-expert architecture and training recipe, and show in controlled simulation and physical-
robot experiments that embodiment midtraining improves downstream adaptation. The resulting Rho variants for YAM Box, UR AI Trainer, and FR3 Duo match or outperform existing open-weights VLAs and achieve the strongest overall performance across the tasks, embodiments, and baselines evaluated in this report. We further demonstrate the Rho model family's built-in capacity for online adaptation: an internal latent policy learns from corrective feedback to select observation-conditioned noise inputs for the frozen flow-matching action expert. With as few as 15 corrected episodes, adapting this lightweight module enables Rho to handle task situations at the fringe of its offline finetuning distribution. Together, these results position Rho as both a strong general-purpose robotic manipulation model and a practical foundation for adaptation. We release the base Rho model and the embodiment-specific checkpoints to facilitate Rho's deployment in research experiments and practical industrial use cases.
Read the full abstract ▾
All authors Rho Team: Simran Bagaria, Daphne Chen, Dean Fortier, Jianlong Fu, Michael Harrison, Tess Hellebrekers, Neel Joshi, Andrey Kolobov, Dalton Moore, Galen Mullins, Michael Murray, Eduardo Salinas, Reuben Tan
Computer Vision
Rethinking Representations for World-Action Modeling
Haoyi Jiang, Liu Liu, Xinjiang Wang et al. (+12 more)
World-action models jointly learn
robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure effective policy learning. These findings motivate ReWAM, a representation-centric world-action model built on pre-trained DINO features. Feature Calibration and a Temporal Representation Bottleneck organize these features into compact world states suited to dynamics modeling. Action-Grounded Representation Shaping routes only action-loss gradients to the bottleneck, thereby letting the policy shape what the representation encodes while the world model learns how it evolves. Without generative
video pre-training, ReWAM achieves 93.6% success on RoboTwin 2.0. On RoboDojo, it achieves an average score of 12.29 and a success rate of 8.28% using approximately 600 hours of
embodied pre-training data.
Read the full abstract ▾
All authors Haoyi Jiang, Liu Liu, Xinjiang Wang, Zhihao Sun, Zequn Chen, Sen Wang, Xinjie Wang, Xia Chen, Jingfeng Yao, Weiheng Zhao, Shanglin Yuan, Zhizhong Su, Wei Sui, Wenyu Liu, Xinggang Wang
Game Theory
Why Last-Iterate Scale-Invariant Regret Matching Converges Linearly?
Boning Li and Longbo Huang
IREG-PRM+ normalizes the cumulative regret vector by its own norm and attains optimal regret without knowledge of the payoff scale. Run unmodified on zero-sum
matrix games, it converges linearly in the last iterate, and no analysis explains why. The obstacle is that the
algorithm has no fixed step size to analyze: the step size is a state variable, the inverse of a regret norm that the trajectory itself moves. Every proved linear rate for regret-matching dynamics comes from restarting or modifying the update. We identify the mechanism as norm saturation: the regret norm rises to a finite limit and freezes the step size. We prove that it always does, with an explicit bound, and that saturation forces the last-iterate Nash gap to vanish on every
matrix game; pointwise convergence follows whenever the
equilibrium is unique. Near a unique strictly complementary
equilibrium the active support freezes in one step, and the one-round Jacobian on that support has a closed form. The last-iterate then converges linearly at a closed-form rate, provided one scale-invariant quantity stays below one: the saturated step size times the largest singular value of the value-centered payoff submatrix on the support. On the $216$-instance testbed, the $184$ instances with a resolvable limit all satisfy it. The same analysis gives a ratio certificate: observable norm-increment ratios bound the unobservable Nash-gap ratio up to a constant that enters once and does not accumulate with the iteration count. Its slope-two law holds on $96.1\%$ of the instances where the slope is measurable, and the same increment monitors progress in extensive-form games, where best-response passes can be scheduled sparsely. The code is available at https://github.com/lbn187/NormCert.
Read the full abstract ▾
Machine Learning
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization
Jianru Shen
Evaluations of graph reconstruction by
language models typically report a single aggregate distance between the original and the reconstructed graph. We prove that for the Wasserstein distance between
Laplacian spectra such a summary is bracketed by two edge counts, the net change in edge number from below and the symmetric difference from above, each scaled by $2/n$ where $n$ is the number of vertices. The bracket is sharp: its two ends coincide exactly when the reconstruction only adds edges or only deletes them, and on that class the distance is a rescaled edge count that says nothing about which edges changed. When the ends differ, the residual between the distance and the lower end is positive only if the reconstruction both invented and lost edges, which turns it into a certificate of mixed editing computable from the reported summaries alone. We characterize these regimes in 135 reconstructions produced by three open-weight models over 45 synthetic graphs. Seventy-seven outputs are one-sided and 29 mixed outputs have $X > 0$, including cases where edge count is exactly preserved while nineteen edges were simultaneously invented and lost. The three models differ in editing policy, ranging from copying the input to attempting completion at the cost of large
hallucination volume, a distinction that aggregate distortion does not reveal.
Read the full abstract ▾
Information Theory
An information identity reveals the geometry of deviation events
Akshay Balsubramani
In a deviation event, the empirical measure of $n$ independent draws lands in a set of distributions. The exponent of its probability splits, at every $n$, into two nonnegative terms. The first is the rate: $n$ times the relative
entropy, from the population, of the distribution of a typical draw under the event. The second is the dependence that conditioning induces among the draws, measured by their total correlation. Their relative sizes depend on the geometry of the set. This paper focuses on this exact split and on the geometry that the interplay of its two terms reveals. The dependence vanishes exactly when the event confines every draw to a single set, and the classical rate of that constraint is exact. On a set invariant under a compact group that fixes the population and leaves no invariant set of intermediate probability, the rate vanishes; uniform convergence over a hypothesis class that such a group permutes is one. On a half-space whose threshold sits a fixed number of standard errors above the mean, the fraction of the exponent that is dependence tends to a function of the event's probability alone. On a set split into pieces, the dependence is the pieces' average plus $n$ times the Jensen-Shannon divergence of their marginals, minus the
entropy of their weights. The split extends to a general reference law. When the information projection is such a law, the split gives the exact value of the expectation in the exponential change of measure to the projection.
Read the full abstract ▾
Sound
EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
Kuan-Po Huang, Haohe Liu, Puyuan Peng et al. (+5 more)
Emotion-conditioned text-to-
speech (TTS) models may fail to express the requested
emotion reliably, and improving controllability by additional training is costly in both computation and
emotion-labeled
speech training data. We therefore study vector steering, a training-free approach that modifies the internal representations of a frozen model. CoCoEmo, a conventional vector steering method for
emotion TTS, treats each
emotion vector as an indivisible direction controlled by a single global strength, limiting adherence to the requested
emotion. In this work, we first discover that an
emotion vector can be decomposed into a shared component that moves
speech away from neutral expression and a residual component that directs generation toward the requested
emotion. Building on this finding, we propose
Emotion Residual-Enhanced Steering for TTS (EmoRES), a novel method that controls the two components without retraining the backbone. On IEMOCAP, EmoRES outperforms CoCoEmo across all four objective
emotion metrics on the IndexTTS-2 and CosyVoice2 backbones. Rank correlation improves by 26.13 and 12.97 percentage points, corresponding to relative gains of 118.8% and 33.1%, while
emotion hit rate improves by 12.95 and 6.92 points, corresponding to relative gains of 20.1% and 9.8%. Human evaluation further shows a relative improvement up to 35.0% in the rate at which listeners correctly identified the dominant requested
emotion and up to a 17.3% improvement in fidelity, while listeners prefer EmoRES for naturalness in up to 63.8% of pairwise comparisons. Component ablations further demonstrate that effective control benefits from preserving the shared component while strengthening the residual of the
emotion steering vectors.
Read the full abstract ▾
All authors Kuan-Po Huang, Haohe Liu, Puyuan Peng, Haibin Wu, Zhaoheng Ni, Hung-yi Lee, Jinwon Lee, Neha Chachra