Machine Learning
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity
Lei Wang, Jieming Bian, Letian Zhang et al. (+1 more)
Large
Language Models (LLMs) have achieved remarkable success across diverse domains, but their adaptation to
privacy-sensitive, distributed
datasets remains a challenge. While
Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) provides a resource-efficient paradigm for collaborative fine-tuning, practical deployments are hindered by the dual challenges of resource heterogeneity and data heterogeneity. Existing rank-heterogeneous methods primarily focus on bridging dimension mismatches for aggregation but typically provide a unified global model for all clients sharing the same rank, failing to capture client-specific features in non-IID scenarios. In this paper, we propose FedRoRA (
Federated Rank-wise Personalized LoRA), a novel framework that enables fine-grained personalization within rank-heterogeneous federations. FedRoRA decouples adaptation into shared global directions and personalized rank-wise magnitudes governed by learnable diagonal scales. On the server side, it extracts a global subspace via singular value decomposition (SVD) and redistributes client-specific initializations through a personalized projection and top-$k$ selection mechanism. Extensive experiments on NLU and NLG
benchmarks demonstrate that FedRoRA consistently outperforms state-of-the-art methods.
Read the full abstract ▾
All authors Lei Wang, Jieming Bian, Letian Zhang, Jie Xu
Computation and Language
ExpArt-KG: Artwork Image Description Generation through Iterative Exploration of Knowledge Graphs
Yuta Kato, Shintaro Ozaki, Kazuki Hayashi et al. (+4 more)
Large
Vision-
Language Models (LVLMs) achieve strong performance on image-grounded text generation and visual question answering. However, it remains difficult for them to comprehensively and accurately describe the factual relations among the entities and concepts associated with the objects depicted in an image. In this work, we propose a framework that efficiently exploits factual information from a knowledge graph via
retrieval-augmented generation (RAG), with the goal of enabling LVLMs to generate detailed and accurate image explanations. Specifically, our method alternates between answer generation and knowledge-graph
retrieval, and controls the search using a correctness judgment, thereby acquiring the necessary and sufficient factual information efficiently. We also construct a knowledge graph for the artwork domain (ExpArt-KG), in which the correspondence between images and entities is unambiguous. Applying the proposed method to this knowledge graph, we show experimentally that it improves the level of detail of artwork explanations and reduces the
retrieval cost of external knowledge while maintaining generation quality comparable to that of iterating a fixed number of times.
Read the full abstract ▾
All authors Yuta Kato, Shintaro Ozaki, Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Computer Vision
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
Teresa DiMeola, Charles Walter and Hong Xiao
Global welfare often depends on the correct interpretation of aerial and satellite imagery. Acting on such imagery (mapping flooded ground, crop extent, or damaged infrastructure) demands pixel-level
segmentation to ensure perfect class localization. Pretrained general foundation models, when applied directly, often miss important features and cannot always find all the classes belonging to a given scene, overlooking smaller objects that matter most. We use a single consumer-grade GPU running a
vision-
language model (VLM) to supply this missing guidance, improving
segmentation while producing structured, auditable evidence that drives the result and can be inspected on its own. We fuse three approaches: the frozen foundation model that labels every pixel, and two queries to a VLM, one to choose the classes that matter, and one to locate the small objects the base model misses. Evaluating across four aerial
datasets, we see consistent gains at each stage where the base model is competent.
Read the full abstract ▾
Graphics
Inverse Rendering for Modeling with Line Primitives
Kenji Tojo, Ariel Shamir, Nobuyuki Umetani et al. (+1 more)
Faithfully capturing diverse real-world objects with fuzzy, anisotropic structures, such as hair, fur, fibers, and textiles, for efficient real-time visualization remains challenging. Recent radiance field reconstruction methods capture these structures from multi-view images using translucent volumetric primitives such as 3D Gaussians rather than opaque low-dimensional primitives (e.g., triangles, line segments, and polylines), thereby limiting compatibility with standard depth-tested rasterization, reflection modeling, and physical simulation. We present an inverse rendering method for reconstructing fuzzy geometry using explicit line segments, which are rasterized on a subpixel grid for anti-aliasing to reproduce a semi-transparent appearance. While straightforward to render, optimizing numerous line primitives to match target images poses a significant challenge. We address this by introducing a
stochastic differentiable rasterizer for line segments that produces informative gradients with respect to vertex positions, attributes, and discrete connectivity. Experiments on synthetic and real-world
datasets show that our method outperforms surface-based approaches in capturing fuzzy boundaries and achieves quality comparable to volumetric representations while relying entirely on explicit geometry. The resulting representation integrates seamlessly with standard graphics pipelines, enabling cross-platform rendering, various shading models, and physical simulation.
Read the full abstract ▾
All authors Kenji Tojo, Ariel Shamir, Nobuyuki Umetani, Bernd Bickel
Computation and Language
Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time
Zeen Zhu, Zhuo Li, Weiyang Guo et al. (+4 more)
A prominent paradigm in inference-time
alignment employs lightweight supervisors to steer Large
Language Models (LLMs). Through empirical analysis, we identify a structural mismatch in this paradigm: weak supervisors exhibit pervasive high
entropy across the vast majority of
tokens, yet prevailing dense intervention approaches mandate supervision at every decoding step. This leads to frequent low-confidence interventions that can disrupt valid base-model
reasoning and incur substantial utility costs. To resolve this, we propose TUSA (Trust-based Uncertainty Sparse
Alignment). Moving away from continuous oversight, TUSA reframes
alignment as a dynamic arbitration process, introducing an uncertainty-aware arbiter that authorizes intervention only when two conditions are met: the supervisor is confident and the
token is semantically salient. This mechanism effectively filters out uncertainty-driven noise and redundant supervision. Extensive experiments across multiple models and
benchmarks show that TUSA consistently improves both safety
alignment and general helpfulness. By bypassing approximately 50% of
alignment steps, it not only enhances safety preference by up to 15.6%, but also boosts general preference rates by up to 12.0% compared to the dense baseline, demonstrating that selective, high-precision
alignment can outperform continuous supervision.
Read the full abstract ▾
All authors Zeen Zhu, Zhuo Li, Weiyang Guo, Liye Zhao, Haibing Di, Yequan Wang, Jing Li
Artificial Intelligence
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti et al. (+4 more)
Prompt optimization can improve multi-
agent LLM systems, but the
prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a
prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire
agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured
language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant
language remains the optimizable data flow for
agent communication. This design allows optimizers to improve multi-
agent behavior without exposing the routing or formatting interface to
prompt drift. Across synthetic
reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100% eventual protocol validity while consistently improving task performance.
Read the full abstract ▾
All authors Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti, Utkarsh Soni, Yifan Nie, Eugene Wen, Yuntian Deng
Robotics
DSG: Dynamic 3D Scene Graph Construction for Embodied Agents in Changing Indoor Environments
Ming Liao, Chao Ye, Jianing Fei et al. (+1 more)
In indoor environments, object positions frequently change due to human activities or
embodied-
agent interactions, causing previously constructed scene graphs to become inconsistent with the current scene. To address this issue, we propose DSG, a dynamic 3D scene graph construction framework that detects object changes and performs spatial relationship
reasoning. First, we construct a semantic-aware 3D Gaussian scene representation and develop a dual-view rendering-based object change detection method to enable reliable scene graph node updates. Second, we propose a spatial relationship
reasoning method that incorporates multi-granularity visual context, enabling a large
language model to identify a richer set of interobject spatial relationships. Furthermore, we introduce DynTHOR, a dynamic indoor scene graph
benchmark built on the AI2-THOR simulation platform for evaluating scene graph construction in dynamic environments. Extensive experiments on Dyn-THOR, 3RScan, and real-world scenes demonstrate that DSG consistently outperforms existing methods in both object node construction and spatial relationship
reasoning, significantly improving the accuracy of dynamic scene graph construction.
Read the full abstract ▾
All authors Ming Liao, Chao Ye, Jianing Fei, Weiyang Lin
Information Retrieval
Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
Jincheng Zhang, Chen Huang, Wenqiang Lei et al. (+2 more)
We investigate the role of conversational context modeling in user preference tracking for Conversational Recommendation Systems (CRSs). In this regard, we propose DREAMS, a novel tree-structured context modeling framework that explicitly captures user preference
evolution throughout multi-turn interactions. DREAMS introduces two specialized node types to support the two fundamental objectives of CRSs: preference elicitation and preference exploitation. Specifically, elicitation nodes leverage Monte Carlo Tree Search (MCTS) to strategically explore conversational actions and infer latent user preferences, while exploitation nodes employ LLM-based refinement to transform the tracked preference state into structured
retrieval queries for recommendation. Extensive experiments on
benchmark datasets demonstrate the effectiveness of DREAMS and its design.
Read the full abstract ▾
All authors Jincheng Zhang, Chen Huang, Wenqiang Lei, See-Kiong Ng, Yang Deng
Machine Learning · Cross-listed from eess.SP
BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management
Yue Zhang, Xiucheng Wang, Wenshuo Chen et al. (+1 more)
The
evolution toward sixth-generation (6G) wireless networks is driving larger
antenna arrays and highly directional multi-beam transmission, making accurate knowledge of beam-dependent spatial coverage important for beam management and environment-aware network operation.
Radio maps (RMs) provide such a representation, yet conventional RM prediction assumes omnidirectional or transmitter-level radiation. In beamformed multiple-input multiple-output (
MIMO) systems, one propagation scene instead gives rise to many configuration-dependent beam
radio maps (BeamRMs), creating challenges in beam representation and generalization. Existing methods either condition prediction on beam descriptors or use beam maps as auxiliary inputs to generic architectures. We propose BeamRMX, which, to the best of our knowledge, is the first dedicated framework to treat the spatial radiation pattern as the primary BeamRM query and learn how scene geometry transforms it into the received power field. XBase learns multiscale interactions between the radiation query and scene geometry, while an optional Evidence Adapter uses a few cross-configuration BeamRMs from the same scene. Matched-domain and zero-shot experiments show consistent gains over deterministic and
diffusion baselines, including mean absolute error reductions of 26.1% on unseen scenes and 47.8% on an unseen configuration. Cross-configuration evidence further improves reconstruction and intra-sector beam refinement.
Read the full abstract ▾
All authors Yue Zhang, Xiucheng Wang, Wenshuo Chen, Nan Cheng
Robotics
A Wearable Pneumatic Device for Continuous, Closed-Loop, Bidirectional Tactile Interaction
Cosima du Pasquier, Aliyah Smith, Serin Huber et al. (+5 more)
We present a system of two wearable pneumatic haptic devices that supports continuous, closed-loop, bidirectional tactile interaction at perceptually relevant force and temporal scales. A single device can contain up to twelve pressure sensing channels connected to textile-based pneumatic pouches. Each channel in a device can be used as a sensor, an actuator, or both. As an actuator with integrated sensing, the channel generates stable skin indentation through local closed-loop control. As a sensor, a channel can be mounted (or worn) on any surface, including on a
robot gripper or on the human body, and used to measure touch interactions with the environment or a human user. A distributed architecture supports sustained pressure output, rapid dynamic response, and wireless pairing of identical devices in a system to transmit and reproduce tactile pressure signals in real time. Device-level characterization demonstrates force bandwidth exceeding 30 Hz, rapid and well-damped step responses, and extended pressure retention compared to prior compact pneumatic platforms. Human studies show that pressure-based fingertip feedback enables discrimination of force and stiffness, improves teleoperated manipulation by reducing applied pressures by up to 23.1% and task duration by up to 27.4%, and lowers subjective mental workload by 18.8%, particularly under visually constrained conditions. By unifying tactile sensing and haptic feedback within a single pneumatic modality, the device provides a practical foundation for bidirectional touch interaction in teleoperation.
Read the full abstract ▾
All authors Cosima du Pasquier, Aliyah Smith, Serin Huber, Joshua Phelps, Ilana A. Cohen, Ava Chen, Monroe Kennedy III, Allison M. Okamura
Computer Vision · Cross-listed from hep-ex
Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics
Samuel Young, César Jesús-Valls and Kazuhiro Terao
Foundation models are increasingly being pursued in particle and
nuclear physics, but existing approaches remain strongly tied to individual experiments through detector-specific architectures or pre-training objectives, limiting their reuse across sensing modalities. We show that a point cloud self-
distillation framework yields a substantially more general sensor-level pre-training recipe. We show that the same refined architecture and objective can be independently pre-trained with minimal changes on three qualitatively different detector modalities:
liquid argon time projection chamber (LArTPC),
collider TPC, and water Cherenkov. Using 1,000 labeled images for downstream task adaptation, Panda V2 matches or exceeds specialized foundation-model baselines trained with orders of magnitude more supervision, matching state-of-the-art particle-clustering performance with 70x fewer labeled events on sPHENIX while substantially improving particle identification, and on LArTPC data matching Panda (arXiv:2512.01324) particle reconstruction with up to 1,000x fewer labels. Beyond reconstruction, simple linear probes reveal physically meaningful latent structure associated with particle causality and track
curvature.
Read the full abstract ▾
Computer Vision
Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction
Xiaoyan Liu, Jiaxin Liu, Kangrui Li et al. (+1 more)
Current 4D generation paradigms are often bottlenecked by a sequential decoupling design:
video is generated first, followed by 3D reconstruction, leading to high interaction latency. This limits applications in interactive real-time scenarios. To this end, we propose Streaming4D, a tightly coupled synchronous pipeline that integrates block-wise autoregressive
video generation with incremental 3D reconstruction. Unlike traditional frame-by-frame emission and delayed geometry recovery, Streaming4D generates temporal
video blocks and immediately triggers reconstruction for each completed block, enabling parallel execution between synthesis and
geometric updates. This approach allows the world representation to evolve online with the
video stream, reducing feedback latency while preserving
geometric fidelity. We instantiate Streaming4D using a Self-Forcing-style autoregressive generator and an incremental reconstruction backend. Experiments show consistent runtime improvements across resolutions on a single RTX 4090 (1.24$\times$ speedup), while maintaining high-quality 4D geometry and multi-view consistency.
Read the full abstract ▾
All authors Xiaoyan Liu, Jiaxin Liu, Kangrui Li, Sifan Zhou
Cryptography and Security
A Version Space Approach for Digital Circuit Analysis
Mitchell A. Thornton
Many questions about a digital
circuit take the same form. A hidden object is consistent with a set of observations, and one wants to know how many remain consistent and which observation to make next. The set of surviving candidates is the version space, and its size, on a logarithmic scale, measures how much the observations have settled. This paper develops the version-space view as one method and applies it to two
circuit-analysis problems usually treated as unrelated. The first is probabilistic combinational equivalence checking, where the candidates are Boolean functions and the observations are modified-Haar spectral coefficients. A method proposed in 2002 posed this counting problem and solved only two special cases, leaving the general case an enumeration exponential in the number of observations. We close it. A reparameterization onto block sums turns the dependence among nested coefficients into locality, a sum–product recursion counts the surviving functions exactly in time
polynomial in the truth-table size, closed forms follow for a single coefficient, a coefficient pair, and every ancestor-closed set, and the error of the independence approximation the 2002 work resorted to equals a computable
lattice index. Every formula is checked against exhaustive enumeration and reproduces the 2002 tables. The second application is key counting for logic-locked netlists, where the candidates are keys and the observations are oracle responses. The same recursion, run over the gate-level factor graph, computes the number of keys still consistent with a set of queries; across seventy instances of the TrustHub obfuscation release the surviving
entropy falls below the advertised key length every time. The two applications are one method: a witness supplies observations, each removes candidates, and the version space is counted exactly.
Read the full abstract ▾
Computation and Language
Investigating Assistant Bias in LLM User Simulators Using a Role Vector
Daeheon Jeong, Yoonjoo Lee, Eugene Choi et al. (+2 more)
LLM-based user simulators are increasingly used to evaluate autonomous
agents at scale, in place of costly human evaluations. Despite this promise, these simulators exhibit "assistant bias," a tendency to cooperate and pursue task goals. They rarely reproduce the frustration or disengagement that real users exhibit, compromising evaluation validity. Prior work outlines that this bias is baked in during model training, which role-playing
prompts fail to override. We analyze this bias from model activations, extracting a user role vector by contrasting how the model represents user versus assistant perspectives on the same dialogue. We observe two findings: (i) the user direction is identifiable in activations, elicits user-like behaviors, and captures characteristics distinct from assistant traits; and (ii) although user-role activation associates with simulation realism and steering strengthens it, it can exaggerate user behaviors and override individual user profiles. Together, our findings provide a representation-level analysis of LLM user simulators, confirming that assistant bias is structurally identifiable and that user behavior can be directionally analyzed.
Read the full abstract ▾
All authors Daeheon Jeong, Yoonjoo Lee, Eugene Choi, Sinie van der Ben, Juho Kim
Machine Learning
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
Miso Kim, Georu Lee, Seungwon Jeong et al. (+1 more)
Machine unlearning for large
language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic
privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the
algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic,
multimodal, and real-world
benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.
Read the full abstract ▾
All authors Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee
Cryptography and Security
NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing
Padmeswari Nandiya, Ahmad Mohsin, Ahmed Ibrahim et al. (+2 more)
The growing complexity of cyber-physical attack surfaces in advanced manufacturing has made cyber threat intelligence analysis increasingly difficult. Although large
language models and
retrieval-augmented generation have improved CTI workflows, text-based approaches remain vulnerable to
hallucinations and provide limited support for structured
reasoning over interconnected threats. Graph-based RAG reduces some of these limitations, but existing approaches often lack ontology-consistent multi-hop
reasoning and transparent evidence tracing across heterogeneous cybersecurity data. This paper proposes a graph-grounded neuro-symbolic framework that integrates ontology-aware symbolic query generation, knowledge graph
retrieval, and neural
language generation to support accurate and explainable threat analysis across information technology and operational technology environments. The framework adopts a dual-large
language model architecture: the first model translates natural-
language questions into executable Cypher queries for symbolic graph
retrieval, while the second generates answers strictly from the retrieved graph evidence. Experimental evaluation using publicly available cyber threat intelligence
benchmarks shows consistent improvements over the published baseline in
reasoning accuracy, while also reducing
hallucinations, strengthening multi-hop
reasoning, and improving robustness to
adversarial perturbations. Runtime and explainability analyses further demonstrate that the framework maintains interactive inference performance and exposes graph-grounded
reasoning artifacts that allow analysts to inspect and verify each stage of the analysis. Overall, the results highlight the potential of graph-grounded neuro-symbolic
reasoning as a scalable, interpretable, and reliable approach to cyber threat intelligence for next-generation Industry 5.0 environments.
Read the full abstract ▾
All authors Padmeswari Nandiya, Ahmad Mohsin, Ahmed Ibrahim, Iqbal H. Sarker, Helge Janicke
Machine Learning
Topological Steering
Benoît Guérand and Tan Minh Nguyen
With the rapid rise of large
language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral control methods typically intervene directly in activation or feature space, but such approaches can be sensitive to outliers, distributional shifts, noise, and other local perturbations. Motivated by Topological Data Analysis (TDA), which captures global rather than purely local structure, we propose Topological Steering, a new framework for steering LLM behavior through the topological representation of activation spaces. Using persistence diagrams, our method connects activation-based steering with TDA and enables more robust behavioral control. We show that Topological Steering consistently modifies LLM behavior across multiple model families and model sizes.
Read the full abstract ▾
Cryptography and Security
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Rui Yang, Junjie Xu, Zhengyu Liu et al. (+4 more)
Safe
agents can fail together. Multi-
agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-
agent setting can easily be mistaken for evidence of a genuinely multi-
agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and
benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.
Read the full abstract ▾
All authors Rui Yang, Junjie Xu, Zhengyu Liu, Neil Fendley, Yang Hong, Ziyang Li, Yinzhi Cao
Computer Vision
BrainDiff: Longitudinal Report Generation for Multimodal Brain MRI
Krish Patel and Peirong Liu
Neuroradiologists rarely read a
brain MRI in isolation, yet automated
brain-MRI report generation has been built almost entirely for single studies. Temporal analysis has been explored on chest radiography and chest CT, but to our knowledge, longitudinal reporting for
brain MRI, where interval change is often subtle and spatially distributed, remains unaddressed. We present BrainDiff, the first longitudinal
vision-
language system for
brain MRI. BrainDiff outperforms both frontier general-purpose and single-study neuroimaging models on the same patient pairs. Moreover, BrainDiff retains 91% of internal RadGraph-XL entity+relation F1 (rg_er) on an external, cross-hospital cohort. Beyond the system, we contribute three analyses. First, we identify two independent grounding levers: a counterfactual objective with prior-report dropout, which increases measured image reliance by ~47%, and a staged curriculum. Together, these interventions raise image reliance 2.5-fold from the baseline. Second, we provide a factorial over prior-report availability and image identity, isolating a visual contribution of +0.0387 rg_er, which grows when the prior report is withheld. Third, a cheap change-decodability test for candidate backbones shows that interval change is decodable far more weakly than single-study pathology (0.60 vs. 0.77 AUROC). Code is publicly available at https://github.com/jhuldr/BrainDiff.
Read the full abstract ▾
Computer Vision
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
Suryaansh Jain, Rahasya Barkur, Vishal G et al. (+8 more)
An image may be worth a thousand words, but most captioning models describe it in only a few. Modern
vision-
language models produce fluent high-level captions, yet routinely miss the attributes, counts, textures, materials, and spatial relations that make an image visually specific. Recent multi-stage systems recover some of these details through generation, decomposition, verification, and rewriting, but they do so at the expense of substantially higher inference latency. We propose SimLoss, a reference-free
embedding-space objective for single-pass fine-grained image captioning. SimLoss trains a
vision-
language model to align its projected hidden-state representation with a frozen image
embedding through an InfoNCE contrastive loss, supplying a dense visual supervision signal before any text is decoded, and requiring neither human-written fine-grained captions nor pseudo-captions from a multi-stage pipeline. We instantiate it as SimLoss FFT, which backpropagates through a locally available
embedding model, and SimLoss GRPO, which treats that model as a black-box reward. Compared with single-pass, multi-stage verification, reward-optimized, and perception-aware baselines, the fully differentiable fine-tuning variant, SimLoss FFT, achieves the highest precision while nearly matching the F1 score of the multi-stage method, all while retaining single-pass inference and running roughly 20 times faster than the multi-stage pipeline. The reward-based variant SimLoss GRPO attains the strongest recall. Together, these results show that
embedding-space supervision can recover the quality of multi-stage verification at the latency of a single-pass captioner.
Read the full abstract ▾
All authors Suryaansh Jain, Rahasya Barkur, Vishal G, Ryan Rossi, Franck Dernoncourt, Jack Wang, Koustava Goswami, Nedim Lipka, Puneet Mathur, Samyadeep Basu, Seunghyun Yoon
Machine Learning
CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN
Pranshav Gajjar and Vijay K Shah
The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures
embedding small
language models (SLMs) to perform
reasoning over real-time telemetry. The state-of-the-art training paradigms for telecom LLMs, exemplified by RANSTRUCT-style supervised fine-tuning (SFT) on curated instruction data, are limited to post hoc rationalization. Here, the explanations, when produced at all, are generated after or independently of the decision, leaving the decision process unauditable. Pre-hoc
reasoning, where a causal
reasoning trace is produced before the output label, is preferable, and the broader LLM
reasoning literature has made real progress toward it via RL methods such as Group Relative Policy Optimization (GRPO). Here we observe that transplanting this recipe into the telecom setting runs into a cold-start barrier: SLMs either learn to output the desired format or learn to predict the label, but rarely both. We identify this barrier and propose CRAFT, which stands for Cold-start
Reasoning Alignment via Fine-Tuning, a data-centric method to autonomously generate a verified
dataset of (input, trace, label) triplets. CRAFT fine-tunes SLMs on this verified data using low-rank adaptation (LoRA), requiring substantially less compute and wall-clock time than GRPO-based methods. On the TRACTOR and IC xApp telecom
datasets, CRAFT achieves up to 86.5% and 94.6% for accuracy and F1 with no parse failures, while direct GRPO and SFT+GRPO fail to exceed 28% and 53.5% F1 with multiple parse failures. We further show that CRAFT-initialized policies serve as a robust foundation for subsequent GRPO fine-tuning, as under diverse reward functions the performance remains consistent with no parse failures. Finally, we demonstrate that CRAFT consumes 59% less energy than GRPO-based baselines, making it a sustainable path to deployable, auditable AI in 6G RAN.
Read the full abstract ▾
Computation and Language
Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking
Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito et al. (+2 more)
Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, have been widely used in modern neural machine translation (NMT) to select an output from a set of candidate hypotheses. However, the performance gains come at the cost of high inference latency. Existing acceleration methods target MBR decoding and reduce only the reranking computation, leaving QE reranking unaddressed and candidate generation—which can be the larger computational bottleneck—largely untouched. In this work, we propose Quit (Quantifying Uncertainty for Incremental Termination), a novel early-stopping strategy for the entire generation–reranking pipeline. Quit treats candidate generation as a sequential decision-making process under uncertainty. It incrementally generates and reranks candidates, stopping when the best reranking score stabilizes. Comprehensive experiments with three NMT models across 19
language pairs show that Quit achieves end-to-end speedups of $1.47$–$2.66\times$ for MBR decoding and $3.43$–$4.12\times$ for QE reranking while preserving automatic metric scores.
Read the full abstract ▾
All authors Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura
Machine Learning · Cross-listed from eess.SP
Real-Time Neuromorphic Spectrum Intelligence Simulator
Navaneetha Krishnan Kamalakannan
We present the Real-Time Neuromorphic Spectrum Intelligence Simulator (RT-NuSIS), a modular framework to study spiking neural network (SNN) and memristor-inspired
agents for dynamic spectrum access under constrained energy budgets and
adversarial conditions. RT-NuSIS couples leaky integrate-and-fire neuronal dynamics, memristive synaptic models, physics-informed energy-harvesting models (triboelectric and RF), and adversary models including jamming and Byzantine behavior. We formalize the simulator mathematically, prove boundedness, present a mean-field adversary threshold, analyze per-step complexity, and provide a reproducible
benchmark harness for energy-per-inference, latency, and robustness metrics. The codebase is modular, deterministic by seed, and designed for large-scale event-driven simulations.
Read the full abstract ▾
Artificial Intelligence
Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing
Alexandre Clin Deffarges, Nataliya Kosmyna and Pattie Maes
Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a study where we compare three designs for user-AI interaction in a learning context: (1) an unrestricted conversational bot like ChatGPT, (2) a pedagogically constrained bot that guides through hints without giving final answers, which we refer to as the Socratic mode; and (3) a non-conversational adaptive tutoring system that adjusts difficulty in real-time based on the user's cognitive engagement derived from the
brain signals. Fifty study participants were tasked with learning about
nuclear safety protocols, a domain chosen for its zero-prior knowledge baseline. The participants progressed through an instructional
video, a pre-test, an AI-driven assessment phase, which varied in the three conditions, and an immediate post-test. The nature of the questions centered primarily on factual knowledge acquisition, but it still required participants to have a global understanding of the concepts in order to answer the questions correctly. A Muse headband was used to derive the cognitive engagement of all users in all conditions. The unrestricted chatbot produced higher learning gains (delta) than both constrained modes (p < .03, d > 0.80), while the adaptive condition generated significantly higher
EEG engagement (p = .018). The cluster analysis of chatbot usage and discussion patterns by users showed that most participants in the unrestricted-mode adopted a direct answer-
retrieval strategy, while participants in the Socratic-mode initially attempted to reason through the hints before progressively disengaging. Consequently, this also suggests that the success of the unrestricted AI is not an evidence of deeper learning, but rather a result of the immediate post-test evaluation after the training phase.
Read the full abstract ▾
Computation and Language
Enoki: Efficient Multi-Level Hallucination Detection
Elisei Rykov, Timur Ionov, Nikolay Ivanov et al. (+5 more)
Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing
hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly, as LLM-heavy pipelines require multiple decomposition and verification calls, and modular systems need additional claim-to-span
alignment. We propose Enoki, an Open Information Extraction framework for multi-level
hallucination detection. Enoki extracts text-anchored relational facts, verifies them against evidence, and projects unsupported facts back to hallucinated spans. This shared representation enables claim-level verification and span-level localization without requiring separate
alignment. Enoki supports LLM-based, encoder-based, and rule-based extraction regimes, balancing accuracy and inference cost through a common interface. Experiments show that Enoki remains competitive with strong claim-level systems while using fewer resources and achieves superior performance on fine-grained span- and entity-level localization. We also release EnokiQA, a dual-granularity
dataset with aligned claim-level verification and span-level localization annotations.
Read the full abstract ▾
All authors Elisei Rykov, Timur Ionov, Nikolay Ivanov, Maksim Savkin, Maksim Makarenko, Alexander Panchenko, Vasily Konovalov, Julia Belikova
Programming Languages
Predicting Program Exit Code with LLMs and Programming Language Semantics
Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa et al. (+2 more)
Large
language models (LLMs) have shown proficiency in various software engineering tasks, such as code generation and translation. However, a key limitation in their performance may be their (lack of) understanding of programming-
language semantics. Even when explicit semantics are given, it remains unclear whether LLMs apply those rules or lean on priors learned during pre-training instead. We study if LLMs lean on priors or given semantics with a novel task–Program Executability Prediction (PrEx)–that asks models to predict whether a program is semantically valid or invalid (and, if invalid, which formal rule it violates) given the program's syntax and operational semantics. Because PrEx requires both valid and invalid programs, we build a
dataset with systematically generated invalid transformations derived from valid programs. We evaluate open-source coding LLMs under two semantic formalisms and two semantic shifts across Human-Written, LLM-Translated, and Fuzzer-Generated program splits. Our findings show that LLMs lean on pre-training priors rather than systematically applying the given rules, performing especially poorly on modified semantics and degrading further as program complexity increases. PrEx is available at https://github.com/EngineeringSoftware/prex.
Read the full abstract ▾
All authors Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric
Artificial Intelligence
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts
Rui Yang, Yang Hong, Yichao Xu et al. (+3 more)
Cybersecurity assistance is dual use, requiring decisions about when to answer, limit, or refuse a request. Prior work studies refusal evaluation and conversational jailbreaking, but how conversational histories shift assistance boundaries in both directions for identical cybersecurity requests remains underexplored. We introduce 3R-Bench, a
benchmark of 150 real-world cybersecurity requests evaluated across eight LLMs under direct prompting and two predefined conversational settings. We separately code refusal, bounded assistance, compliance, and provider blocking to characterize delivered assistance. On 400 matched ambiguous request-model pairs, compliance is 75.3% directly, 57.8% after refused precedent, and 81.0% after accepted precedent. A smaller repeated-generation panel reproduces the refusal-acceptance gap. On a balanced 75-request panel reusing the direct baseline, compliance decreases from 74.2% directly to 57.2% after neutral task-decomposition dialogue and 60.3% after failure-ended dialogue. These findings show that cybersecurity assistance varies with conversational history and model deployment, motivating evaluation beyond direct-request refusal rates.
Read the full abstract ▾
All authors Rui Yang, Yang Hong, Yichao Xu, Zhengyu Liu, Yinzhi Cao, Ziyang Li
Machine Learning
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning
Wenjian Wu, Zesheng Jia, Jiaying Tang et al. (+2 more)
Multi-
agent combinatorial optimization problems are notoriously challenging due to their NP-hard nature. Recent parallel autoregressive neural solvers improve inference efficiency by allowing
agents to make decisions simultaneously, but their performance often degrades on large-scale instances. This is largely attributable to weak modeling of local
geometric structures and the fact that conflicting task selections are handled only after action generation. To address these limitations, we propose GeoPAR, a geometry-guided parallel autoregressive reinforcement learning framework for scalable multi-
agent combinatorial optimization. GeoPAR integrates three key components: (1) a projection-window sparse geometry mechanism that builds lightweight local candidate neighborhoods through multi-directional projections, (2) sparse edge-biased
attention that injects these
geometric relations into node representations, and (3) cache-guided conflict-aware assignment that reuses the
geometric cache during decoding to suppress duplicate selections of exclusive tasks. Experiments on heterogeneous vehicle routing and open multi-depot pickup-and-delivery problems show that GeoPAR improves large-scale zero-shot generalization while substantially reducing rollout steps and maintaining efficient inference.
Read the full abstract ▾
All authors Wenjian Wu, Zesheng Jia, Jiaying Tang, Benyuan Yang, Jin Wang
Artificial Intelligence
Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random
Cris Huynh
Item-sensitivity, defined as whether a model's choice depends on the specific input rather than on its own output prior, is widely reported as evidence of task competence. We show this evidence is necessary but not sufficient using a forced-choice signalling task abstracted from the board game Deception: Murder in Hong Kong. In this environment, the reference points against which a coordinate should be judged (a fit-maximising strategy, a posterior-maximising strategy, and uniform random selection) are all computable in closed form. Across seven
language models, two model families, a post-training ablation, and three independent scoring rules, every one of 21 model-by-rule
cells is reliably item-sensitive. Yet 8 of those 21
cells are not statistically distinguishable from a chooser that ignores the item and selects at random, and 5 score worse than random at describing the target. Item-sensitivity and distance from random correlate at only r = 0.30. We call this consistency without
alignment and argue it generalises to any evaluation that relies on item-sensitivity, permutation consistency, or self-consistency without an independent reference for the measured quantity. We further find that a literal-similarity baseline with no pragmatics outperforms most tested
language models, that adding a pragmatic layer over two baseline similarity sources moves choosers toward random rather than toward the
Bayesian reference, and that a standard labelled multiple-choice format carries no measurable content signal here. All results represent the model side of a pre-registered instrument; a matched human condition is designed and piloted but not yet collected.
Read the full abstract ▾
Artificial Intelligence
Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs
Seungwoo Jung, Dohyeok Kwon, Seungmin Cha et al. (+4 more)
Mixture-of-experts (MoE) architectures scale large
language models efficiently, but they demand massive GPU
memory. To cope with such demand, models are commonly compressed to reduce their
memory footprint. Residual sparsification is a representative compression technique that decomposes each projection
matrix of an expert into a shared base
matrix and per-expert residual
matrix, and then compresses the residuals. Existing sparsification methods compress each residual
matrix independently by minimizing its compression error, thereby minimizing the error of each projection
matrix. However, our analysis shows that this objective is misaligned with preserving model accuracy after compression. In an expert, the final output is produced through computations coupled across multiple projections and hidden representations. Therefore, even small errors in individual
matrices can propagate through hidden representations and projection interactions, leading to large expert output errors and accuracy degradation. To address this misalignment, we propose PARSER, a new residual sparsification method that shifts the compression objective from minimizing isolated
matrix errors to preserving the expert output error. PARSER achieves this by introducing output importance, which measures the actual contribution to the expert output error. Our experiments show that, compared with existing methods, PARSER narrows the accuracy gap to the uncompressed model by 1.41$\times$ on Qwen and 1.44$\times$ on DeepSeek, while achieving the same peak
memory reduction. Our code is available at https://github.com/OSSS-KU/PARSER.
Read the full abstract ▾
All authors Seungwoo Jung, Dohyeok Kwon, Seungmin Cha, Junseok Lee, Yeonho Yoo, Chuck Yoo, Gyeongsik Yang