arXiv:2602.16171v2 Announce Type: replace
Abstract: Directional ion transport across membranes maintains living systems in nonequilibrium, which underlies chemiosmotic energy conversion. However, the physical origin of collectively organized ion transport in primitive cellular systems remains unclear. Here, we propose a minimal model in which ion pumps collectively align through feedback between ion transport and electrostatic interactions. In the model, directional ion transport generates a membrane potential, while the resulting electrochemical potential biases pump orientation, leading to self-organized collective alignment. Numerical simulations and mean-field analysis reveal a nonequilibrium transition from a disordered state without net transport to a pump-alignment state with sustained membrane potentials. The critical behavior is consistent with the mean-field Ising universality class; however, the effective field is generated self-consistently by nonequilibrium ion transport. We further show that protocell asymmetry can bias the polarity of the membrane potential. These results provide a generic self-organizing mechanism for the emergence of bioelectricity and a physical route toward chemiosmotic coupling in protocells.
Science Journals
arXiv:2605.18334v1 Announce Type: new
Abstract: While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration. Specifically, symmetric kernels struggle to capture shape and color discontinuities , which cause blurriness and primitive redundancy that mislead human perception during visual analysis. To address these visualization barriers, we introduce 3D Skew Gaussian Splatting (3DSGS), a novel framework that significantly enhances the structural fidelity and compactness of explicit scene representations. Our key insight lies in extending the standard primitive to a general Skew Gaussian counterpart. This generalized primitive inherits the highly efficient rasterization properties of standard Gaussians while gaining intrinsic asymmetric modeling capabilities. We couple this with an enhanced opacity representation to better handle complex transparency, alongside a depth-aware densification strategy that intelligently manages primitive allocation. Furthermore, to make these advancements actionable for real-world visual analytics, we re-derive the CUDA rasterization pipeline to universally support both symmetric and skew Gaussians, integrating it into a decoupled, free-camera interactive visualization engine. Extensive experiments demonstrate that 3DSGS achieves superior rendering quality and structural compactness, particularly in regions with intricate details, while maintaining the real-time frame rates necessary for fluid interactive exploration. Supplementary derivations and visual results are available at \textbf{\textit{https://3d-skew-gs.github.io/}}.
arXiv:2605.18165v1 Announce Type: new
Abstract: Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel decoding, this process incurs substantial computational cost due to the large chunk size of masked tokens. We observe that much of this cost is spent on repeatedly processing the preceding context and many [MASK] tokens with the same feature representations, indicating considerable computational redundancy. In this work, we revisit dLLM's redundancy from the perspective of [MASK] tokens. Through systematic analysis, we verify the redundancy of [MASK] tokens while revealing their critical role in providing structural information. Guided by these findings, we propose position-preserving [MASK] token compression and terminal-aware augmentation. By compressing redundant [MASK] computation, this approach accelerates decoding and further provides a natural extension toward context-folding-like long-context scaling under limited input-length constraints for full-sequence dLLMs such as LLaDA-8B-Instruct and LLaDA-1.5. Moreover, for block dLLMs such as LLaDA2.0-mini, it augments the context with a protected terminal [MASK] token to enhance generation quality with negligible overhead.
arXiv:2605.17903v1 Announce Type: new
Abstract: We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlapping chunks of text. Convex mixing of these chunk FCMs gives a representative cyclic FCM knowledge graph. The text chunks can have different levels of overlap. The chunk FCMs still mix to form a new FCM causal knowledge graph. The mixing technique scales because it uses light computation with sparse causal chunk matrices. The mixing structure allows an operator-level type of Bayesian inference that produces "de-chunked" or posterior-like FCMs from the mixed FCM. These de-chunked FCMs are useful in their own right and allow further iterations of Bayesian updating. We demonstrate these mixing techniques on the essay text of Allison's "Thucydides Trap" model of conflict between a dominant power such as the United States and a rising power such as China. The FCM dynamical systems predict outcomes as they equilibrate to fixed-point or limit-cycle attractors. Seven out of 8 FCM knowledge graphs predicted a type of war when we stimulated them by turning on and keeping on the concept node that stands for the rising power's ambition and entitlement. Gemini 3.1 LLMs served as the chunking AI agents.
arXiv:2605.17904v1 Announce Type: new
Abstract: Few-Shot Medical Image Segmentation (FSMIS) aims to delineate novel anatomical targets from one or a few annotated support images, addressing the annotation scarcity in medical imaging. Notwithstanding recent advancements, current prototype-based methods are bottlenecked by two coupled limitations: 1) cue entanglement, where a single spatial-domain prototype is forced to summarise organ silhouette, parenchymal texture and boundary appearance simultaneously, so any support-query mismatch on one cue propagates indiscriminately to the others; and 2) topology-blind matching, where cosine similarity measures distance in the ambient Euclidean space and ignores the connectivity of the underlying feature manifold, causing fragmented activations inside low-contrast organs and leakage into neighbouring tissues. To this end, we propose Spectral-Geodesic Prototype Network (SGP-Net), built around a Spectral-Geodesic Prototype Module with two coupled components. A Spectral Prototype Bank (SPB) decomposes support and query features into low-, mid- and high-frequency bands via learnable radial Fourier filters, yielding three disentangled prototypes per class that separately encode shape, texture and boundary cues. A Geodesic Matcher (GM) then replaces cosine similarity with a differentiable heat-diffusion approximation of geodesic distance, propagating matching signals along a feature affinity graph so that on-manifold pixels accumulate consistent responses while off-manifold look-alikes are suppressed. Experiments on three public FSMIS benchmarks demonstrate that SGP-Net achieves competitive performance against recent state-of-the-art methods.
arXiv:2605.17907v1 Announce Type: new
Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality heterogeneity remains a key barrier to effective fusion. Most existing methods, including direct adaption and protocol-based transformation, typically rely on training adapters for newly emerging feature modalities and often require additional retraining or fine-tuning. Such repeated training is costly and is often infeasible across manufacturers due to model and data privacy constraints, limiting real-world scalability. To address this issue, we propose UniTrans, a universal any-to-any feature modality translation model that instantiates translators on the fly for arbitrary modalities.
UniTrans pretrains a bank of translator expert parameters and learns their combination coefficients as a function of source-to-target modality mapping. The mapping is measured in a modality-intrinsic latent space, where an intrinsic encoder extracts modality-specific yet scene-invariant codes from single-frame intermediate features, enabling UniTrans to instantiate translators in a zero-shot manner.
Experiments on OPV2V-H and DAIR-V2X demonstrate that UniTrans consistently outperforms state-of-the-art methods in both simulated and real-world settings, enabling efficient any-to-any translation through a universal model. The code is available at https://github.com/CheeryLeeyy/UniTrans.
arXiv:2605.18379v1 Announce Type: new
Abstract: Correlated-noise mechanisms are among the most promising approaches for improving the utility of differentially private model training, but rigorous guarantees require explicit, analyzable factorizations, and practical deployment requires memory efficiency. Recent works have developed banded inverse factorizations, which address both requirements by exploiting a banded structure in the correlation matrix. The bandwidth controls the size of the noise buffer used to correlate noise across iterations, and thus governs the tradeoff between utility and memory cost. Existing factorizations highlight this tradeoff: DP-$\lambda$CGD achieves high memory efficiency by using only a one-step noise buffer, but this limits its utility gains, while the banded inverse square root (BISR) factorization exploits larger correlation windows and is asymptotically optimal for large bandwidths but performs poorly at low bandwidths. We propose $\gamma$-BIFR, a unified generalization of both factorizations. In the low-memory, low-bandwidth regime, $\gamma$-BIFR significantly improves RMSE, amplified RMSE, and private training performance, while yielding tighter theoretical guarantees for multi-participation error in multi-epoch training.
arXiv:2605.18163v1 Announce Type: new
Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet hallucination reduction is usually instantiated through one fixed intervention form: contrast one layer against another, steer along a truthfulness direction, or defer to external evidence. This framing is structurally incomplete. Cross-layer factual evidence does not evolve uniformly: in some failures truthful support is present internally and later suppressed, whereas in others candidate competition remains genuinely multi-directional across depth, so no single signed scalar family is generally sufficient. We introduce Trajectory Correction from Cross-layer Evidence for Hallucination Reduction (TRACE), a deterministic, training-free algorithm which corrects hallucinations at inference time by deriving both the corrective layer and the appropriate correction operator from each input's cross-layer candidate trajectory inside the LLM's own forward pass. Under one frozen hyperparameter setting, TRACE selects among scalar reversal, earlier-state recovery, and candidate-space correction using only model-internal evidence. Evaluated as a single universal algorithm across 15 models, 8 model families, and 3 factuality benchmarks, TRACE improves every evaluation cell, yielding mean gains of +12.26 MC1 points and +8.65 MC2-style points with no regressions, with gains reaching +47.20 MC1 and +43.38 MC2-style points. The method uses no labels, retrieval, pretraining, finetuning, or per-model calibration.
arXiv:2605.17936v1 Announce Type: new
Abstract: Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger sequence is used to attack the model. Although these attacks are successful, the triggers generated by such attacks are ungrammatical and unnatural. Our work proposes a novel technique combining parts-of-speech filtering and perplexity based loss function to generate sensible triggers that are closer to natural phrases. For the task of sentiment analysis on the SST dataset, the method produces sensible triggers that achieve accuracies as low as 0.04 and 0.12 for flipping positive to negative predictions and vice-versa. To build robust models, we also perform adversarial training using the generated triggers that increases the accuracy of the model from 0.12 to 0.48. We aim to illustrate that adversarial attacks can be made difficult to detect by generating sensible triggers, and to facilitate robust model development through relevant defenses.
arXiv:2512.23978v2 Announce Type: replace
Abstract: Generative artificial intelligence (GenAI) is shifting from conversational assistants toward agentic systems -- autonomous decision-making systems that sense, decide, and act within operational workflows. This shift creates an autonomy paradox: as GenAI systems are granted greater operational autonomy, they should, by design, embody more formal structure, more explicit constraints, and stronger tail-risk discipline. We argue that stochastic generative models can be fragile in operational domains unless paired with mechanisms that provide verifiable feasibility, robustness to distribution shift, and stress testing under high-consequence scenarios. To address this challenge, we develop a conceptual framework for assured autonomy grounded in operations research (OR), built on two complementary approaches. First, flow-based generative models frame generation as deterministic transport characterized by an ordinary differential equation, enabling auditability, constraint-aware generation, and connections to optimal transport, robust optimization, and sequential decision control. Second, operational safety is formulated through an adversarial robustness lens: decision rules are evaluated against worst-case perturbations within uncertainty or ambiguity sets, making unmodeled risks part of the design. This framework clarifies how increasing autonomy shifts OR's role from solver to guardrail to system architect, with responsibility for control logic, incentive protocols, monitoring regimes, and safety boundaries. These elements define a research agenda for assured autonomy in safety-critical, reliability-sensitive operational domains.
arXiv:2512.23994v4 Announce Type: replace
Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. Previous benchmarks primarily focus on audio-video temporal synchronization, while largely overlooking explicit evaluation of audio-physics grounding, thereby limiting the study of physically plausible audio-visual generation. To address this issue, we present PhyAVBench, the first benchmark that systematically evaluates the audio-physics grounding capabilities of T2AV, image-to-audio-video (I2AV), and video-to-audio (V2A) models. PhyAVBench offers PhyAV-Sound-11K, a new dataset of 25.5 hours of 11,605 audible videos collected from 184 participants to ensure diversity and avoid data leakage. It contains 337 paired-prompt groups with controlled physical variations that drive sound differences, each grounded with an average of 17 videos and spanning 6 audio-physics dimensions and 41 fine-grained test points. Each prompt pair is annotated with the physical factors underlying their acoustic differences. Importantly, PhyAVBench leverages paired text prompts to evaluate this capability. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST) and introduce a novel metric, the Contrastive Physical Response Score (CPRS), which quantifies the acoustic consistency between generated videos and their real-world counterparts. We conduct a comprehensive evaluation of 17 state-of-the-art models. Our results reveal that even leading commercial models struggle with fundamental audio-physical phenomena, exposing a critical gap beyond audio-visual synchronization and pointing to future research directions. We hope PhyAVBench will serve as a foundation for advancing physically grounded audio-visual generation. Prompts, ground-truth, and generated video samples are available at https://github.com/imxtx/PhyAVBench.
arXiv:2605.18375v1 Announce Type: new
Abstract: Distributed Acoustic Sensing (DAS) converts existing fibre-optic cables into dense seismic arrays at near-zero deployment cost, but measures strain rate rather than particle velocity -- the quantity required by virtually all seismological analysis tools. Converting strain rate to particle velocity by numerical integration is ill-posed: the integration constant is undefined and noise accumulates without bound. We present DANTE (DAS-to-velocity via physics-informed neural operator for Acoustic-wave recoNstruction in heTErogeneous media), a Fourier Neural Operator (FNO) trained entirely on synthetic data that enforces two physics constraints: (i) the exact kinematic relation between DAS strain rate and the spatial gradient of particle velocity, and (ii) the one-dimensional elastic wave equation. These constraints resolve the undetermined integration constant and suppress noise without requiring co-located seismometers. On a test set of 200 heterogeneous synthetic wavefields, DANTE achieves a mean output SNR of $15.3 \pm 8.8$ dB, Pearson correlation $r = 0.907$, and SSIM $= 0.976$, corresponding to a mean SNR improvement of approximately $+15$ dB over the best conventional baseline (trace stacking, $n = 10$, $0.02 \pm 0.06$ dB), and up to $+28.8$ dB on the most challenging samples. Zero-shot inference on seven real microseismic events from the Utah FORGE 2019 DAS dataset yields a kinematic residual of 0.003--0.005, five times lower than the synthetic test baseline, confirming generalisation to real field data with no fine-tuning and no seismometers.
arXiv:2605.17865v1 Announce Type: new
Abstract: LiDARs are being increasingly deployed for consumer imaging in handheld, wearable, and robotic applications. These sensors can capture the time-of-flight of light at picosecond resolution, which in principle, enables them to capture information about objects hidden from their field of view. While such non-line-of-sight (NLOS) imaging capabilities have been shown on research-grade LiDARs, they are challenging to achieve on consumer devices due to poor signal quality resulting from low laser power, low spatial resolution, and object and camera motion. Inspired by burst photography and synthetic aperture radar, we propose a multi-frame fusion strategy to overcome these challenges and demonstrate NLOS imaging on consumer LiDAR. We first introduce the motion-induced aperture sampling model to unify the effects of object shape, object motion, and camera motion under a single measurement model. Using this model, we demonstrate several NLOS capabilities on a smartphone-grade LiDAR: (1) 3D reconstruction, (2) single and multi-object tracking, and (3) camera localization using hidden objects. Previously, NLOS imaging capabilities were largely restricted to bulky and expensive research-grade hardware that requires extensive setup and calibration. Our results represent a shift towards plug-and-play NLOS imaging, where anyone can image hidden objects with off-the-shelf hardware ($<100) and no additional setup. We believe that democratization of such capabilities will advance consumer applications of NLOS imaging.
arXiv:2605.17938v1 Announce Type: new
Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world setups. In this paper, we take a decisive step towards more reliable and robust TDA for diffusion models. We propose to perform TDA with mirrored unlearning and noise-consistent skew (MUCS). The idea is to fine-tune a second model with bounded mirrored gradient ascent, and to measure the normalized skew of this model with respect to the original one using consistent noise samples. We show that, while being conceptually simple and generic, MUCS systematically outperforms existing methods on three different datasets by a large margin. We additionally study the effect that core design choices have on final performance, and analyze novel aspects regarding the overlap of influential instances across generated items and the potential of ensembling TDA approaches. We believe that our findings may have broader implications for more general unlearning setups, as well as for tasks requiring the comparison of diffusion losses.
arXiv:2605.18125v1 Announce Type: new
Abstract: We study the problem of connecting the parts of a multipartite graph using a minimum number of edges under a matching constraint. We introduce interconnection trees, defined as matchings whose projections onto the quotient graph form a spanning tree. Motivated by applications in chemoinformatics, we investigate the decision, counting, and enumeration variants of this problem.
We show that the decision problem is $NP$-complete. Nevertheless, it becomes tractable in several structured settings: it is fixed-parameter tractable in the number of parts, and admits polynomial or linear-time algorithms on complete, quasi-complete, and $t$-quasi-complete multipartite graphs. We also study enumeration, for which we design efficient flashlight-search based algorithms with optimal delay for complete multipartite graphs, and a weight-guided heuristic that prioritizes low-weight solutions and performs well in practice.
arXiv:2605.18104v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a representation-geometric perspective by analyzing a text-aligned refusal direction and a modality-induced drift direction. We show that multimodal inputs compress the usable separation along the refusal direction, making it no longer reliable for identifying and refusing harmful inputs. We refer to this failure mode as Safety Geometry Collapse. We quantify it through conditional refusal separability and show that stronger modality-induced drift is consistently associated with weaker refusal separability and higher attack success rates. We then validate the causal role of modality-induced drift through a fixed-strength activation intervention: counteracting the estimated drift restores refusal separability and improves multimodal safety. After drift correction, we further observe self-rectification, where the model recovers its ability to recognize and refuse harmful multimodal inputs during forward dynamics. This effect also provides an internal signal of the model's perceived harmfulness of each input. Motivated by this signal, we propose ReGap, a training-free inference-time method that adaptively corrects modality drift using self-rectification. Experiments across multiple multimodal safety benchmarks and utility benchmarks demonstrate the effectiveness of ReGap, which significantly improves the safety of MLLMs without compromising general capabilities. Our findings highlight representation-level modality alignment as a crucial direction for real-time safety improvement and for building safer, more reliable MLLMs.
arXiv:2511.06316v3 Announce Type: replace
Abstract: In low- and middle-income countries, public safety and urban planning initiatives frequently face a critical shortage of accurate, location-specific road crash data. Extracting reliable geospatial information from unstructured text requires overcoming the limitations of traditional text-based geocoding tools, which often fail in multilingual environments with ambiguous place descriptions. This study introduces ALIGN (Accident Location Inference through Geo-Spatial Neural Reasoning), a vision-language framework designed to emulate human spatial reasoning to infer precise accident coordinates from unstructured Bangla news reports and map-based cues. A multi stage automated pipeline was developed to process diverse textual and visual data, integrating large language models for cue extraction with vision-language models for map verification. Using an agentic architecture, we modelled an iterative reasoning loop that combines Optical Character Recognition (OCR), grid-based spatial scanning, and a 3-run geometric voting method to mathematically isolate and reduce visual hallucinations. The findings highlight that the multimodal ALIGN framework significantly outperforms traditional text-only geoparsing baselines. For example, the proposed system successfully reduced the mean localization error from an unusable 10.915 km to a sub-kilometer precision of 0.593 km on a validation dataset. Furthermore, testing the framework against official Dhaka Metropolitan Police records confirmed its reliability by achieving a mean error of 0.465 km. The results provide a high-accuracy, training-free foundation for automated crash mapping in data-scarce regions, supporting evidence-driven road-safety policymaking and the integration of multimodal AI in transportation analytics.
arXiv:2512.24497v3 Announce Type: replace
Abstract: A long-standing challenge in AI is to develop agents capable of solving a wide range of physical tasks and generalizing to new, unseen tasks and environments. A popular recent approach involves training a world model from state-action trajectories and subsequently use it with a planning algorithm to solve new tasks. Planning is commonly performed in the input space, but a recent family of methods has introduced planning algorithms that optimize in the learned representation space of the world model, with the promise that abstracting irrelevant details yields more efficient planning. In this work, we characterize models from this family as JEPA-WMs and investigate the technical choices that make algorithms from this class work. We propose a comprehensive study of several key components with the objective of finding the optimal approach within the family. We conducted experiments using both simulated environments and real-world robotic data, and studied how the model architecture, the training objective, and the planning algorithm affect planning success. We combine our findings to propose a model that outperforms two established baselines, DINO-WM and V-JEPA-2-AC, in both navigation and manipulation tasks. Code, data and checkpoints are available at https://github.com/facebookresearch/jepa-wms.
arXiv:2603.20904v5 Announce Type: replace-cross
Abstract: Spectral gaps, Kramers escape rates, and position-dependent relaxation timescales are dynamical invariants encoded in the infinitesimal generator $\Lop$ of a stochastic flow. We show that weak projection of the governing It\^{o} SDE onto temporal test functions produces an endogeneity bias of order $O(T\,\dt^{3/2})$ that grows with the observation window and cannot be eliminated by additional data. Projecting instead onto spatial Gaussian kernels removes the bias exactly: $\mathcal{F}_{t_n}$-measurability and the tower property guarantee unbiased regression rows at every step. The resulting framework jointly identifies the drift $b(x)$ and diffusion $a(x)$ from a single sparse regression, producing an explicit symbolic enerator amenable to spectral analysis. Validation on three benchmark systems yields coefficient errors below 5%, stationary-density total-variation distances below 0.01, and autocorrelation functions that faithfully reproduce true relaxation timescales.
arXiv:2602.11699v3 Announce Type: replace
Abstract: Nonsensical and anomalous sentences have been instrumental in the development of computational models of semantic interpretation. A core challenge is to distinguish between what is merely anomalous (but can be interpreted given a supporting context) and what is truly nonsensical. However, it is unclear (a) how nonsensical, rather than merely anomalous, existing datasets are; and (b) how well LLMs can make this distinction. In this paper, we answer both questions by collecting sensicality judgments from human raters and LLMs on sentences from five semantically deviant datasets: both context-free and when providing a context. We find that raters consider most sentences at most anomalous, and only a few as properly nonsensical. We also show that LLMs are substantially skilled in generating plausible contexts for anomalous cases.
arXiv:2602.10937v3 Announce Type: replace
Abstract: Directly solving graded materials from amplitude and phase was a method developed following transformation optics (TO), which provided reflectionless media for an incidence wave. However, this inverting method gives Hermitian media thus not applicable to non-Hermitian (NH) photonics. In this Letter we then design NH media offering more freedom to manipulate waves of no reflection. Our picture of curved-space powered with gain and loss, is exemplified by three types: amplitude controlling, phase conversion, and direction shunting. These examples showcase precise wave manipulation in a surprisingly simple manner, which goes beyond convectional TOs and is implementable in nonreciprocal photonic platform.
arXiv:2309.11965v4 Announce Type: replace
Abstract: In this paper, coordination control of discrete event systems under joint sensor and actuator attacks is investigated. Sensor attacks are described by a set of attack languages using a proposed ALTER model. Several local supervisors are used to control the system. The goal is to design local supervisors to ensure safety of the system even under cyber attacks (CA). The necessary and sufficient conditions for the existence of such supervisors are derived in terms of conditional decomposability, CA-controllability and CA-observability. A method is developed to calculate local state estimates under sensor attacks. Two methods are also developed to design local supervisors, one for discrete event systems satisfying conditional decomposability, CA-controllability and CA-observability, and one for discrete event systems satisfying conditional decomposability only. The approach works for both stealthy and non-stealthy attacks. A practical example is given to illustrate the results.
arXiv:2412.18158v2 Announce Type: replace
Abstract: Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specialization limits their versatility and requires costly retraining for new applications. To address this, we introduce UniCodec, a universal codec built on a novel paradigm of semantic disentanglement at the encoder and compositional generation at the decoder. This framework is designed to simultaneously serve both human and machine needs, eliminating the need for task-specific retraining. At the encoder, UniCodec leverages pre-generated, task-specific label codebooks created by a Large Language Model (LLM). For any given task, a grounding model uses the corresponding codebook to perform task-aware disentanglement, compressing only the most relevant image regions. This mechanism not only saves significant bits but is also the key to our system's rapid, zero-retraining adaptation: switching to a new task is as simple as selecting a new codebook. The decoder then performs compositional generation: it combines the compact, disentangled components with powerful priors from a generative diffusion model. This process reconstructs a high-quality, complete image optimized with rich detail for human perception and precise features for machine vision tasks. Extensive experiments demonstrate that UniCodec consistently outperforms existing methods, effectively bridging the gap between human-centric and machine-centric compression.
arXiv:2505.20218v2 Announce Type: replace
Abstract: Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise prediction paradigms that overlook synergistic drug effects and potential adverse drug-drug interactions (DDIs). We propose FLAME, a fine-grained list-wise alignment framework for large language models (LLMs), enabling drug-by-drug generation of drug lists. FLAME formulates recommendation as a sequential decision process, where each step adds or removes a single drug. To provide fine-grained learning signals, we devise step-wise Group Relative Policy Optimization (GRPO) with potential-based reward shaping, which explicitly models DDIs and optimizes the contribution of each drug to the overall prescription. Furthermore, FLAME enhances patient modeling by integrating structured clinical knowledge and collaborative information into the representation space of LLMs. Experiments on benchmark datasets demonstrate that FLAME achieves state-of-the-art performance, delivering superior accuracy, controllable safety-accuracy trade-offs, and strong generalization across diverse clinical scenarios. Our code is available at https://github.com/cxfann/Flame.
arXiv:2605.17497v1 Announce Type: new
Abstract: GRPO-style RLVR trains reasoning models from multiple on-policy attempts per prompt, but typically uses these attempts only through terminal rewards. We show that a mixed group contains a richer process signal: a correct completion is a self-generated witness of how the current policy can solve the problem, while a wrong completion provides on-policy prefixes where the policy needs correction. We introduce \emph{Self-Supervised On-Policy Distillation} (SSOPD), which distills a teacher distribution conditioned on the shortest correct completion into prefixes of the longest wrong completion. This converts intra-group correct--wrong contrast into dense process supervision without external solution traces. A stopping-time view motivates the shortest-correct / longest-wrong rule as a finite-group approximation to editing persistent failures toward fast-success actions, and a prompt-level frontier weight concentrates the auxiliary loss where correct and wrong branches coexist. Across AIME 2024, AIME 2025, and HMMT 2025, SSOPD improves over GRPO in all nine model-benchmark settings. On Qwen3-8B, it reaches a macro Avg@12 of 65.6, outperforming GRPO by 1.6 points and the solution-conditioned OPSD baseline by 0.8 points. Code will be released at https://github.com/tzq1999/SSOPD.