arXiv:2606.30636v1 Announce Type: cross Abstract: In this review, we survey the cryptographic task of authentication from the perspective of quantum communication. We review three main flavours of authentication that are often conflated in the literature: authentication of classical messages, authentication of quantum messages, and entity authentication, also covering recent hardware-assisted approaches. We compare representative protocols for each functionality in terms of their security assumptions, set-up requirements, composability, and scalability in large or dynamic networks, and use these criteria to identify and recommend suitable candidates. Finally, applications are surveyed: we provide a detailed case study of authentication and quantum key distribution (QKD), then extend the discussion to protocols beyond QKD, where the role of authentication is more complex. Our take-home message is that an authentication requirement is not an intrinsic limitation of quantum networks: as with all secure communication, each protocol relies on a particular authentication resource, and the security claim of that protocol is meaningful only once the authentication resource and its deployment assumptions are made explicit. At the same time, the existing classical and quantum literature already offers a range of quantum-secure authentication schemes, which can support different applications when carefully matched to the required functionality, assumptions, and security guarantees.
Science Journals
arXiv:2406.03367v2 Announce Type: replace Abstract: Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.
arXiv:2205.05945v3 Announce Type: replace Abstract: We consider in this contribution a simplified idealized one-dimensional model in a nuclear core reactor coupling the diffusion equation on the neutron flux with the enthalpy equation for the water which collects the heat produced by this idealized nuclear core. These equations are coupled through the dependency of the coefficients of the diffusion equation in terms of the enthalpy. We propose a numerical method treating globally the coupled problem for finding its unique solution. Simultaneously, we use incomplete elliptic integrals to represent analytically the density of neutrons and the enthalpy in the fluid. Both methods lead to the same solution with high accuracy. However, another quantity, generally used as a benchmark for comparing results, depends considerably on the approximation used for the coefficients of the diffusion equation.
arXiv:2405.01906v3 Announce Type: replace Abstract: In modern intelligent transportation systems (ITS), particularly in freight transportation and logistics, real-time route planning is crucial. It presents unique challenges driven by high uncertainty in service requests, where the number of service customers can vary drastically, ranging from hundreds to thousands. Existing neural methods struggle to maintain performance under such significant variations, which severely limits their practical applicability. To address this crucial shortcoming, this work proposes a novel Instance-Conditioned Adaptation Model (ICAM) designed for better large-scale generalization. In particular, we design a simple yet efficient instance-conditioned adaptation function that adjusts the policy based on the specific geometry and density of the current traffic scenario to improve model adaptability with minimal computational overhead. Furthermore, we propose a powerful yet low-complexity instance-conditioned adaptation module to generate better solutions for instances across various scales. Extensive experiments on synthetic, benchmark, and real-world instances demonstrate that ICAM can consistently achieve promising generalization performance across four widely studied large-scale route planning scenarios. Notably, our proposed method delivers high-quality solutions with remarkably fast inference speed, providing a scalable and efficient solution for real-time intelligent transportation operations. Our code is available at https://github.com/CIAM-Group/ICAM.
arXiv:2408.07837v2 Announce Type: replace Abstract: Earth's fast rotation imposes the Taylor-Proudman Constraint that opposes fluid motion across an imaginary cylindrical surface called the Tangent Cylinder (TC) obtained by extruding the equatorial perimeter of the solid inner core along the rotation direction, and up to the core-mantle boundary (CMB). To date, however, the influence of this boundary is unknown, and this impedes our understanding of the flow in the polar regions of the core. We reproduce the TC geometry experimentally, where the CMB is modelled as a cold, cylindrical vessel, with a hot cylinder inside it acting as the inner solid core. The vessel is filled with water to optically map the velocity field in regimes of criticality and rotational constraint consistent with those of the Earth. We find that the main new mechanism arises out of the inertia near the cold lateral boundary of the vessel, which drives inertia at the outer boundary of the TC, as convection in the equatorial regions of the Earth's core does. The baroclinicity just outside the TC suppresses the classical wall modes found inside a solid cylinder, and the inertia there causes an early breakup of the TPC at the TC boundary. The flow remains dominated by the Coriolis force even up to criticality of 191, but because of inertia near the TC boundary, geostrophic turbulence appears at much lower criticality than in other settings. The heat flux escapes increasingly through the TC boundary as the TPC becomes weaker. Hence, inertia driven by baroclinicity outside the TC provides a convenient shortcut to geostrophic turbulence, which is otherwise difficult to reach in experiments. These results also highlight a process whereby the convection outside the TC may control turbulence inside it and bypass the axial heat transfer. We finally discuss how Earth's conditions, especially its magnetic field, may change how this process acts within the Earth's core.
arXiv:2408.16028v4 Announce Type: replace Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) are trained on vast unlabelled code corpora, yet perform only marginally better than coin flips when directly prompted to detect vulnerabilities. In this paper, we reframe vulnerability detection as anomaly detection, based on the premise that vulnerable code is rare and thus anomalous relative to patterns learned by LLMs. We introduce ANVIL, which performs a masked code reconstruction task: The LLM reconstructs a masked line of code, and deviations from the original are scored as anomalies. We propose a hybrid anomaly score that combines exact match, cross-entropy loss, prediction confidence, and structural complexity. We evaluate our approach across multiple LLM families, scoring methods, and context sizes, and against vulnerabilities after the LLM's training cut-off. On the PrimeVul dataset, ANVIL outperforms state-of-the-art supervised detectors - LineVul, LineVD, and LLMAO - achieving up to 2x higher Top-3 accuracy, 75% better Normalized MFR, and a significant improvement on ROC-AUC. Finally, by integrating ANVIL with fuzzers, we uncover two previously unknown vulnerabilities, demonstrating the practical utility of anomaly-guided detection.
arXiv:2606.30221v1 Announce Type: new Abstract: Hydrogen-based direct reduction of metal oxides is a ubiquitous solid-gas redox process central to geophysics, sustainable metallurgy, redox energy cycles and catalysis. During this process, hydrogen removes lattice oxygen to form water, yet product water has long been regarded as a passive exhaust, and its nanoscale formation, trapping and removal remain poorly understood. Here, we directly observe redox-product water release from iron oxide during hydrogen-based direct reduction. Because water removal emerges from coupled structural, chemical and crystallographic evolution across multiple length-scales under realistic non-equilibrium reaction-conditions, we establish a correlative multiscale in-situ approach that links pore evolution, molecular water signatures, phase transformation and chemical-state evolution during hematite reduction. We uncover a mechanism in which oxygen removal induces closed nanopores spatially delocalized from reaction surfaces, causing transient trapping of water vapor. Water is released only when these pores coalesce into a percolating network connected to the surface, coinciding with and accelerating the onset of the hematite-to-magnetite transformation. These findings show that dynamically evolving pore topology governs mass transport and redox kinetics in solid-gas reactions, closing a critical mechanistic gap in product-water removal and providing nanoscale guidance for hydrogen-based metal extraction, reactor design, and sustainable redox energy technologies under practical conditions.
arXiv:2409.00654v2 Announce Type: replace Abstract: We introduce Seed-to-Seed Translation (StS), a novel approach that combines GANs and diffusion models (DMs) for unpaired Image-to-Image Translation. Our approach is aimed at global translations of complex automotive scenes, where close adherence to the structure and semantics of the source image is essential. We demonstrate that the semantic information encoded in the space of inverted latents (seeds) of a pretrained DM, dubbed as the seed-space, can be used for discriminative tasks, and leverage this information to perform image-to-image translation. Our method involves training an sts-GAN, an unpaired seed-to-seed translation model, based on CycleGAN. The translated seeds are used as the starting point for the DM's sampling process, while structure preservation is ensured using a ControlNet. We demonstrate the effectiveness of our approach for structure-preserving translation of complex automotive scenes, showcasing superior performance compared to existing GAN-based and diffusion-based methods. In addition to advancing the SoTA in automotive scene translations, our approach offers a fresh perspective on leveraging the semantic information encoded within the seed-space of pretrained DMs for effective image editing and manipulation.
arXiv:2002.11508v3 Announce Type: replace Abstract: TCSPs (Temporal Constraint Satisfaction Problems) [Dechter et al. 1991] get rid of unary constraints by binarizing them after having added an "origin of the world" variable. In this work, we look at the constraints between the "origin of the world" variable and the other variables, as the (binarized) domains of these other variables. With this in mind, we define a notion of arc-consistency for TCSPs, which we will refer to as binarized-domains Arc-Consistency, or bdArc-Consistency for short. We provide an algorithm achieving bdArc-Consistency for a TCSP, which we will refer to as bdAC-3, for it is an adaptation of Mackworth's [1977] well-known arc-consistency algorithm AC-3. We show that if an STP is bdArc-Consistent, and connected, i.e., its "origin of the world" variable is disconnected from none of the other variables, its binarized domains are minimal. We provide two polynomial backtrack-free procedures: one for the task of getting a solution from a connected bdArc-Consistent STP; the other for the task of getting, from a bdArc-Consistent STP, either that it is inconsistent or, in case of consistency, a connected bdArc-Consistent STP refinement. We then show how to use our results both in a general TCSP solver and in a TCSP-based job shop scheduler. The work also provides an experimental comparison on STPs of bdAC-3 with an existing arc-consistency algorithm, ACSTP, restricted to STPs [Kong et al. 2018]; an experimental comparison of three TCSP-based job shop schedulers, two of which use weak versions of bdAC-3 as the filtering procedure during the search, the third [Schwalb and Dechter 1997] a weak version of path-consistency; and the swi-prolog source codes used by these comparisons. Last but not least, we provide an incremental version of bdAC-3.
arXiv:2511.15517v2 Announce Type: replace Abstract: Modern high-throughput BFT consensus protocols use streamlined push-pull mechanisms to disseminate blocks and keep happy-path performance optimal. Yet state-of-the-art designs lack a principled and efficient way to exchange blocks, which leaves them open to targeted attacks and performance collapse under network asynchrony. This work introduces the concept of a block synchronizer, a simple abstraction that drives incremental block retrieval and enforces resource-aware exchange. Its interface and role fit cleanly inside a modern BFT consensus stack. We also uncover a new attack, where an adversary steers honest validators into redundant, uncoordinated pulls that exhaust bandwidth and stall progress. Beluga is a modular and scarcity-aware instantiation of the block synchronizer. It achieves optimal common-case latency while bounding the cost of recovery under faults and adversarial behavior. We integrate Beluga into Mysticeti, the consensus core of the Sui blockchain, and show on a geo-distributed AWS deployment that Beluga sustains optimal performance in the optimistic path and, under attack, delivers up to 3x higher throughput and 25x lower latency than prior designs. The Sui blockchain adopted Beluga in production.
arXiv:2103.09286v5 Announce Type: replace Abstract: In this paper we study generalizations of classical results on intersection patterns of set systems in $\mathbb{R}^d$, such as the fractional Helly theorem or the $(p,q)$-theorem, in the setting of arbitrary triangulable spaces with a forbidden homological minor. Given a simplicial complex $K$ and an integer $b$, we say that a family $\mathcal{F}$ of subcomplexes of some simplicial complex $X$ is a $(K,b)$-free cover if (i) $K$ is a forbidden homological minor of $X$, and (ii) the $j$th reduced Betti number $\tilde{\beta}_j(\bigcap_{S\in {\mathcal{G}}}S,\mathbb{Z}_2)$ is strictly less than $b$ for all $0\leq j < \dim K$ and all nonempty subfamilies $\mathcal{G}\subseteq \mathcal{F}$. We show that for every $K$ and $b$, the fractional Helly number of a $(K,b)$-free cover is at most $\mu(K)+1$, where $\mu(K)$ is the maximum sum of the dimensions of two disjoint faces in $K$. This implies that the assertion of the $(p,q)$-theorem holds for every $p \ge q > \mu(K)$ and every $(K,b)$-free cover $\mathcal{F}$. For $b=1$ and a suitable $K$ this recovers the original $(p,q)$-theorem and its generalization to good covers. Interestingly, our results show that that the range of parameters $(p,q)$ for which the $(p,q)$-theorem holds is independent of $b$. Our proofs use Ramsey-type arguments combined with the notion of stair convexity of Bukh et al. to construct (forbidden) homological minors in certain cubical complexes.
arXiv:2312.14194v2 Announce Type: replace Abstract: This article presents a general solution to the problem of computational complexity. First, it gives a historical introduction to the problem since the revival of the foundational problems of mathematics at the end of the 19th century. Second, building on the theory of functional relations in mathematics, it provides a theoretical framework where we can rigorously distinguish two pairs of concepts: Between solving a problem and verifying the solution to a problem. Between a deterministic and a non-deterministic model of computation. Third, it presents the theory of computational complexity and the difficulties in solving the P versus NP problem. Finally, it gives a complete proof that a certain decision problem in NP has an algorithmic exponential lower bound thus establishing firmly that P is different from NP. The proof presents a new way of approaching the subject: neither by entering into the unmanageable difficulties of proving this type of lower bound for the known NP-complete problems nor by entering into the difficulties regarding the properties of the many complexity classes established since the mid-1970s.
arXiv:2406.03981v2 Announce Type: replace Abstract: We consider a fictitious domain formulation for fluid-structure interaction problems based on a distributed Lagrange multiplier to couple the fluid and solid behaviors. How to deal with the coupling term is crucial since the construction of the associated finite element matrix requires the integration of functions defined over non-matching grids: the exact computation can be performed by intersecting the involved meshes, whereas an approximate coupling matrix can be evaluated on the original meshes by introducing a quadrature error. The purpose of this paper is twofold: we prove that the discrete problem is well-posed also when the coupling term is constructed in approximate way and we discuss quadrature error estimates over non-matching grids.
arXiv:2310.09115v2 Announce Type: replace Abstract: Nondeterministic Discounted-Sum Automata (NDAs) are nondeterministic finite automata equipped with a discounting factor $\lambda>1$, and whose transitions are labelled by weights. The value of a run of an NDA is the discounted sum of the edge weights, where the $i$-th weight is divided by $\lambda^{i}$. NDAs are a useful tool for modelling systems where the values of future events are less influential than immediate ones. While several problems are undecidable or open for NDA, their deterministic fragment (DDA) admits more tractable algorithms. Therefore, determinization of NDAs (i.e., deciding if an NDA has a functionally-equivalent DDA) is desirable. Previous works establish that when $\lambda\in \mathbb{N}$, then every complete NDA, namely an NDA whose states are all accepting and its transition function is complete, is determinizable. This, however, no longer holds when the completeness assumption is dropped. We show that the problem of whether an NDA has an equivalent DDA is decidable when $\lambda\in \mathbb{N}$.
arXiv:2511.18639v2 Announce Type: replace Abstract: We propose a novel framework for developing, analyzing, and validating reductions between NP-complete problems. Powered by the SAT-based constraint solver URSA, our methodology introduces several distinct features that set it apart from other related approaches. The proposed workflow effectively bridges the crucial gap between informal, high-level reduction descriptions and formalized mathematical proofs. By supplementing rather than replacing human intuition, this interactive methodology serves as an aid for exploring relationships between NP-complete problems.
The Societal Implications of Blockchain Technology in the Evolution of Humanity as a "Superorganism"
arXiv:2501.10378v2 Announce Type: replace Abstract: This article examines the broader societal implications of blockchain technology and crypto-assets, emphasizing their role in the evolution of humanity as a "superorganism" with decentralized, self-regulating systems. Drawing on a process philosophy approach grounded in Stiegler's "general organology" and further informed by related concepts such as Nate Hagens' "superorganism" idea and Francis Heylighen's "global brain" theory, the paper contextualizes blockchain technology within the ongoing evolution of governance systems and global systems such as the financial system. Blockchain's decentralized nature, in conjunction with advancements like artificial intelligence and decentralized autonomous organizations (DAOs), could transform traditional financial, economic, and governance structures by enabling the emergence of collective distributed decision-making and global coordination. In parallel, the article aligns blockchain's impact with developmental theories such as Spiral Dynamics. This framework is used to illustrate heuristically blockchain's potential to foster societal growth beyond hierarchical models, promoting a shift from centralized authority to collaborative and self-governed communities. The analysis, grounded in sense-making through a philosophical and biomimetical approach, and aims at providing a holistic narrative and view of blockchain as more than an economic tool, positioning it as a transductive technological seed for the evolution of society into a mature, interconnected global planetary organism.
arXiv:2511.20771v3 Announce Type: replace Abstract: Phylogenetic networks allow modeling reticulate evolution, capturing events such as hybridization and horizontal gene transfer. A fundamental computational problem in this context is the Tree Containment problem, which asks whether a given phylogenetic network is compatible with a given phylogenetic tree. However, the classical statement of the problem is not robust to poorly supported branches in biological data, possibly leading to false negatives. In an effort to address this, a relaxed version that accounts for uncertainty, called Soft Tree Containment, has been introduced by Bentert, Mal\'ik, and Weller [SWAT'18]. We present an algorithm that solves Soft Tree Containment in $2^{O(\Delta_T \cdot k \cdot \log(k))} \cdot n^{O(1)}$ time, where $k = \operatorname{sw}(\Gamma) + \Delta_N$, with $\Delta_T$ and $\Delta_N$ denoting the maximum out-degrees in the tree and the network, respectively, and $\operatorname{sw}(\Gamma)$ denoting the "scanwidth" [Berry, Scornavacca, and Weller, SOFSEM'20] of a given tree extension of the network, while $n$ is the input size. Our approach leverages the fact that phylogenetic networks encountered in practice often exhibit low scanwidth, making the problem more tractable.
arXiv:2412.08108v3 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Existing attacks typically target the vision encoder's final output embeddings, implicitly treating the encoder as a uniform attack surface, while a systematic analysis of which internal components are most vulnerable has remained largely unexplored. We show such analysis is essential, as adversarial vulnerability in LVLM vision encoders is structurally concentrated rather than uniformly distributed. Building on this, we propose Vision Encoder Vulnerable-Component-Targeted Universal Adversarial Perturbation (VEV-UAP), a task-agnostic and cost-efficient attack framework. Through a component- and layer-wise analysis of attention mechanisms, we identify the value components in middle layers as critical vulnerabilities that strongly influence downstream language model behavior. VEV-UAP selectively targets these components to generate a single universal perturbation shared across images, without involving textual inputs or the language model during optimization. Experiments across multiple LVLMs and tasks show VEV-UAP achieves state-of-the-art attack success rates with reduced computational overhead. Moreover, a single VEV-UAP transfers across LVLMs sharing the same vision encoder, even when paired with different language models, making it a practical framework for scalable robustness evaluation.
arXiv:2501.13589v3 Announce Type: replace Abstract: Team Automata is a formalism for interacting component-based systems proposed in 1997, whereby multiple sending and receiving actions from concurrent automata can synchronise. During the past 25+ years, team automata have been studied and applied in many different contexts, involving 25+ researchers and resulting in 25+ publications. In this paper, we first revisit the specific notion of synchronisation and composition of team automata, relating it to other relevant coordination models, such as Reo, BIP, Contract Automata, Choreography Automata, and Multi-Party Session Types. We then identify several aspects that have recently been investigated for team automata and related models. These include communication properties (which are the properties of interest?), realisability (how to decompose a global model into local components?), tool support (what has been automatised or implemented?), and variability (can a family of concrete product (automata) models be captured concisely?). Our presentation of these aspects provides a snapshot of the most recent trends in research on team automata, and delineates a roadmap for future research, both for team automata and for related formalisms.
arXiv:2402.06158v2 Announce Type: replace Abstract: In the rapidly evolving landscape of retail, assortment planning plays a crucial role in determining the success of a business. With the rise of sponsored products and their increasing prominence in online marketplaces, retailers face new challenges in effectively managing their product assortment in the presence of sponsored products. Remarkably, previous research in assortment planning largely overlooks the existence of sponsored products and their potential impact on overall recommendation effectiveness. Instead, they commonly make the simplifying assumption that all products are either organic or non-sponsored. This research gap underscores the necessity for a more thorough investigation of the assortment planning challenge when sponsored products are in play. We formulate the assortment planning problem in the presence of sponsored products as a combinatorial optimization task. The ultimate objective is to compute an assortment plan that optimizes expected revenue while considering the specific requirements of placing sponsored products strategically.
arXiv:2511.21256v2 Announce Type: replace Abstract: Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety-critical scenario evaluation. Unlike the widely studied image modality, in this work we explore generative world models for LiDAR data. Existing generation methods for LiDAR predominantly focus on single frame generation or lack the capacity for interactive simulation, while existing prediction approaches require multiple frames of historical input and can only deterministically predict multiple frames at once. Both paradigms fail to support long-horizon interactive generation. To this end, we introduce \textbf{LaGen}, which, to the best of our knowledge is the first autoregressive framework capable of generating long-horizon LiDAR scenes in a frame-by-frame, interactive manner. LaGen is able to take a single-frame input as a starting point and effectively utilize bounding box information as conditions to generate high-fidelity 4D scene. In addition, we introduce a scene decoupling estimation module to enhance the model's interactive generation capability for object-level content, as well as a noise modulation module to mitigate error accumulation during long-horizon generation. We extensively evaluate LaGen's performance in controlled data generation and long-horizon scene generation on the nuScenes dataset. The experimental results demonstrate that LaGen achieves state-of-the-art performance, especially on later frames. The code is publicly available at: https://github.com/szzhou88/LaGen.
arXiv:2512.06208v3 Announce Type: replace Abstract: Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value. However, input features can be spatially sparse in some image data, where semantic information may occupy only a small fraction of the pixels and most computation would be wasted on empty regions. In this work, we introduce SparsePixels, a framework that implements sparse convolution on FPGAs by selectively retaining and computing on a small subset of active pixels while ignoring the rest. Because computation always runs over a single pre-specified pixel budget, the inference latency is independent of the input sparsity and is constant at runtime. We show that, for identifying neutrino interactions in naturally sparse LArTPC images with 4k pixels, a standard CNN with a compact size of 4k parameters incurs an inference latency of 48.665 $\mu$s on an FPGA, whereas a sparse CNN of the same base architecture, computing on less than 1% of the input pixels, achieves a $\times 73$ speedup to 0.665 $\mu$s with resource utilization well within on-chip budgets, trading only a small percent-level performance loss. This work aims to benefit future algorithm development for efficient data readout in modern experiments with latency requirements of microseconds or below.
arXiv:2507.07056v2 Announce Type: replace Abstract: The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.g., personal portraits) on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs can be weaponized by adversaries to generate harmful content (e.g., political, defamatory imagery), undermining creator rights and platform safety. Existing defenses like concept-erasure methods focus on full diffusion models (DMs), neglecting LoRA's unique role as a modular adapter and its vulnerability to adversarial prompt engineering. To bridge this gap, we propose LoRAShield, the first data-free editing framework for securing LoRA models against misuse. Our platform-driven approach dynamically edits and realigns LoRA's weight subspace via adversarial optimization and semantic augmentation. Experimental results demonstrate that LoRAShield achieves remarkable effectiveness, efficiency, and robustness in blocking malicious generations without sacrificing the functionality of the benign task. By shifting the defense to platforms, LoRAShield enables secure, scalable sharing of personalized models, a critical step toward trustworthy generative ecosystems.
arXiv:2512.06344v2 Announce Type: replace Abstract: Generative image compression has recently shown impressive perceptual quality, but often suffers from semantic inconsistency at ultra-low bitrates (bpp < 0.05), limiting its reliable deployment in bandwidth-constrained scenarios such as 6G semantic communications. This inconsistency stems from incomplete guidance information, which introduces semantic ambiguity into the generation process and may lead to natural-looking but source-inconsistent content. In this work, we propose a Semantic-Disambiguation-Guided Generative Image Compression (SDGIC) framework to constrain diffusion-based reconstruction at ultra-low bitrates. Specifically, SDGIC compresses the source image into three compact and complementary guidance streams: a concise text caption for global semantics, a highly compressed image (HCI) for dense visual evidence, and Reconstruction-Aware Semantic Residual Tokens (RSRTs) for reconstruction-relevant residual semantics that remain ambiguous under the text caption and HCI conditions. The RSRTs are directly optimized toward the downstream denoising objective, enabling them to provide source-specific semantic constraints for disambiguating diffusion-based reconstruction. To inject these three guidance streams into the generation process effectively, we design a Dual-Path Conditioned Diffusion Decoder (DPCD), which uses cross-attention for semantic conditions and ControlNet residuals for dense visual guidance. Extensive experiments demonstrate that SDGIC improves semantic consistency at ultra-low bitrates while maintaining favorable perceptual quality, with a 23.4% reduction in AFINE on the CLIC2020 dataset.
arXiv:2508.06482v2 Announce Type: replace Abstract: Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this behavior. We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation. We evaluate with two new benchmarks focused on this capability. First, we design a focused, cognitively-motivated interaction benchmark that consistently elicits strong convention formation trends in humans. Second, we create a new document-grounded reference completion task that reflects in-the-wild convention formation behavior. Our studies show significantly improved convention formation abilities in post-trained LLMs across the two evaluation methods.