Computer Vision
Think Before You Score: Thinking Reward Model for Visual Generation
Xuehai Bai, Zhenchen Tang, Yang Shi et al. (+9 more)
Visual reward models are essential for evaluating and improving visual generation models, yet existing approaches typically map task conditions and candidate outputs directly to scalar rewards, leaving implicit what should be evaluated for each individual case. We introduce Think Before You Score, a paradigm that explicitly determines what matters for each case before judging how well the candidate performs. Following this principle, we propose the Thinking Reward Model (TRM), which formulates case-adaptive rubrics, performs rubric-guided assessment, and produces fine-grained pointwise rewards. We further observe that conventional pairwise preference optimization can induce score polarization, and introduce Pairwise Dual-Group Relative Policy Optimization (PD-GRPO), which leverages pairwise supervision to improve reward discrimination while preserving fine-grained pointwise scoring. Extensive experiments on image generation and editing reward-modeling
benchmarks demonstrate that TRM achieves state-of-the-art performance among open-source reward models while remaining highly competitive with proprietary alternatives. Moreover, using TRM as a reward for reinforcement learning consistently improves diverse visual generation models, demonstrating that its fine-grained, case-adaptive rewards translate into effective optimization signals for visual generation.
Read the full abstract ▾
All authors Xuehai Bai, Zhenchen Tang, Yang Shi, Dianyi Wang, Tengfei Liu, Wanshun Su, Xuanyu Zhu, Ruohui Wang, Haiwen Diao, Haotian Wang, Xiaoling Gu, Yuanxing Zhang
Computation and Language
Compiling Learning Problems into Adaptation Programs for Language Models
Rebecca Ramnauth and Brian Scassellati
Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcomes. We introduce adaptation compilation, which reframes where, how, and to what extent a model should adapt as a joint prediction and decision problem. Rather than searching over candidate programs anew for each learning episode, a compiler learns from prior adaptations to predict a vector-valued counterfactual response surface over candidate programs—their expected effects on acquisition, transfer, boundedness, and preservation—and selects a program before adaptation begins. Because this predicted geometry captures multiple behavioral consequences rather than a single winner or scalar score, it can be reused under different downstream priorities without retraining. Across five learning types, preferred programs vary meaningfully across episodes, and this variation is predictable from pre-adaptation information. On Llama-3.1-8B, compiler-selected programs approach exhaustive search while outperforming global and objective-specific defaults. Replication on Gemma-2-9B preserves program heterogeneity and selection headroom, but shows that exploiting this headroom requires accounting for uncertainty when departing from strong defaults. Together, these results show that adaptation search can be amortized across related learning problems, turning prior adaptation experience into a basis for deciding how future learning should occur.
Read the full abstract ▾
Human-Computer Interaction
Shaping Opinion: Quantifying the Psychological Impact of Autonomous Multi-Agent LLM Interactions
Marcos Rodriguez-Vega, Afonso Ferreira, Iru Exposito-Luis et al. (+2 more)
Natural-sounding multi-
agent conversational AI is increasingly deployed, fundamentally altering human-machine interaction and human information processing. While prior work largely focuses on algorithmic failure, this study investigates the cognitive ergonomics and socio-cognitive impact of algorithmic competence. We present and evaluate FORMS (Framework for Opinion and Rhetoric in Multi-
agent Simulations), a low-latency architecture for spatially mediated human-machine dialogue, driven by distinct LLM-based personas and real-time concurrency resolution. To conduct a system test and evaluation of its psychological impact, we exposed an adolescent cohort (n=120) and an adult pilot group (n=25) to a live, moderated synthetic debate. Our findings reveal that exposure to highly competent multi-
agent systems triggers "Cognitive Destabilization," fragmenting users' prior strategic consensus. Concurrently, we observe a "Regulatory Awakening" driven by the "Normality Paradox": fluid human-machine interactions inherently increase the baseline demand for external regulation. Furthermore, our pilot study suggests the presence of a "Truthfulness Paradox": despite understanding the risks of generative AI, participants in the adult cohort rated the synthetic debate as significantly more sincere than equivalent human discourse (Cohen's d=2.04). Supported by robust statistical effect sizes, this paper contributes the FORMS architecture and a replicable evaluation protocol, illustrating how high-fidelity conversational systems can reshape human information processing.
Read the full abstract ▾
All authors Marcos Rodriguez-Vega, Afonso Ferreira, Iru Exposito-Luis, Carolina Polito, Pino Caballero-Gil
Information Theory · Cross-listed from quant-ph
A Memory-Magic Exchange Law in Streaming Clifford+T Compilation
Jinze Yang, Yangyang Li and Xiu-Hao Deng
A phase that reaches a fault-tolerant processor in additive pieces can be remembered until the last piece arrives, or executed on arrival: the first option costs classical
memory carried across rounds, the second costs magic states committed before the phase is known. We determine the exchange rate $\alpha$, committed $T$ gates per bit of
memory forgone, for ancilla-free coordinatewise Clifford+$T$ compilation. The Ramanujan bound gives $\alpha\ge2$ with explicit constants, the square-root barrier of the spectral method. An elementary determinant method, using that quaternion numerators lie on spheres in both real
embeddings of $\mathbb{Q}(\sqrt2)$, counts words near any rotation coset below that barrier. With a height dichotomy for the sphere sections it produces and a fibration over rational projections, it gives every $\alpha<5/2$ unconditionally and uniformly over frames, by an exact SMT check of its continuum case analysis; $5/2$ is where this method stops. At Clifford-framed cosets the volume law holds up to subexponential factors: all but a vanishing fraction of $z$-rotations need $T$-count $(3-o(1))\log_2(1/\varepsilon)$, and processes whose committed pieces are near Clifford-framed $z$-rotations, including per-rotation pipelines, have $\alpha\ge3-o(1)$, which a fractional-passthrough family attains under the Ross-Selinger typical-cost hypothesis. Under an equidistribution
conjecture supported by exhaustive enumeration to $T$-count 22, $\alpha=3$ in general and
memory should be shed in whole rotations. The bounds hold even when the phases cancel to the identity; side information enters through a conditional
entropy; probabilistic mixing halves the costs but not the rate. With clean ancillas and a phase-gradient catalyst, table lookups batched over coordinates drive the rate to $O(1/\log\log(1/\varepsilon))$, so the constant-rate law is specific to coordinatewise synthesis.
Read the full abstract ▾
Cryptography and Security
Backdoor Mitigation in Decentralized LLM Fine-Tuning
Sayan Biswas, Jade Garcia Bourrée, Rachid Guerraoui et al. (+5 more)
Decentralized large
language model (LLM) fine-tuning lets organizations collaboratively train a shared LLM on data they cannot pool, without a central coordinator. In every round, each node exchanges a trainable adapter with its neighbors over a communication graph, and then aggregates them. This setting, however, is vulnerable to propagated
backdoors, which is a hidden behavior that lets a model perform normally on clean inputs but produce an attacker-chosen output whenever a secret trigger appears. We show that a single node poisoning its own model can
backdoor adapters of nodes that have never seen a poisoned example, making them refuse
prompts that contain a secret trigger. We present Chorus, a decentralized mechanism that lets each node detect and reject backdoored adapters from its neighbors before aggregation, without requiring shared validation data or any knowledge of the attacker's trigger or target. Chorus judges each adapter by its behavior, using the receiver's own adapter as a trusted reference. Crucially, no node in Chorus judges adapters alone: the receivers of each adapter update probe it independently, pool their findings in the neighborhood, and vote to make a decision. So a
backdoor that slips past one receiver is still caught by the others. We evaluate the effectiveness of Chorus using two instruction-tuning
datasets and LLM architectures, and against a state-of-the-art baseline. Chorus cuts the average attack success rate (ASR) of the attacker's neighbors from 48-63% to at most 2.2%, within 0.6 percentage points of an omniscient oracle that knows the exact malicious nodes. Even the worst-affected honest node never exceeds 10% ASR, the same bound as the oracle, against up to 78% without defense. This all comes at a negligible communication overhead.
Read the full abstract ▾
All authors Sayan Biswas, Jade Garcia Bourrée, Rachid Guerraoui, Maxime Jacovella, Anne-Marie Kermarrec, Sathwika Peechara, Martijn de Vos, Milos Vujasinovic
Game Theory
Sharp Second-Best Welfare in Bilateral and Matching Markets
Zhengyang Liu, Ying Qin and Zihe Wang
How much social welfare must a
market lose because values are private? We determine the sharp ratio of second-best to first-best welfare under independent nonnegative types,
Bayesian incentive compatibility, interim individual rationality, and no expected budget deficit. The ratio is approximately $0.8882516903$ for arbitrary priors and $0.9113893681$ when buyers have monotone hazard rates and sellers are unrestricted. The arbitrary-prior guarantee holds for every downward-closed family of feasible matchings; the MHR guarantee holds when every matching of a compatibility graph is feasible. Both constants are \revise{attained}{sharp} already in bilateral trade. The proof keeps the sellers' initial endowment inside the budget Lagrangian. For arbitrary priors, a common threshold decomposition reduces the problem to three-parameter power-law distributions. For monotone hazards, common transformations of buyer and seller scores reduce it to shifted capped exponential buyers; a typewise allocation certificate and an explicit worst-case seller satisfy the same boundary equation. The bilateral-to-matching framework, with a welfare endowment charge and an MHR-preserving packing argument, transfers these affine inequalities without loss. We give exact variational characterizations of both constants and reproducible interval certificates for their numerical evaluation. Unrestricted signed transfers also permit pointwise strong budget balance.
Read the full abstract ▾
Artificial Intelligence
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Guannan Lai and Han-Jia Ye
Large
language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality–efficiency trade-off of LLM inference. Existing routers are typically learned through local fitting: a router is optimized for a particular query workload and candidate pool, and often requires additional supervision or retraining as the routing environment changes. We ask whether LLM routing can instead be approached from a foundation-model perspective, learning a reusable routing capability that generalizes across tasks, candidate models, and deployment conditions. To this end, we introduce RouteFM, which learns to characterize anonymous candidate models from behavioral context and infer their target-specific capabilities, rather than binding routing decisions to fixed model identities or a single environment. Through episodic pretraining across heterogeneous routing environments, this capability can be reused by a frozen router and adapted to new environments through context alone. Experiments demonstrate transfer across changes in domains, modalities, candidate pools, and context budgets, with the largest gains when behavioral evidence is limited. On MMR-Bench, which is excluded from pretraining, RouteFM outperforms the strongest baseline by 2.23 quality points with only eight observations per candidate. These results support moving LLM routing from repeated local fitting toward a pretrain once, route anywhere paradigm. Our code is publicly available at https://github.com/LAMDA-Model-Reuse/RouteFM.
Read the full abstract ▾
Computation and Language
SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search
Zetong Zhou, Wentao Zhang, Jingyuan Wang et al. (+3 more)
Operations research supports decision-making in domains such as energy, economics, and healthcare. Solving operations research problems typically begins with optimization modeling, which translates a natural-
language problem description into executable solver code. LLMs offer a promising way to automate this process, but they remain prone to errors. In practice, these errors can be divided into two categories: syntactic errors refer to solver code that fails to run successfully or is judged infeasible by the solver; semantic errors refer to solver code that successfully returns an objective value but violates the intent of the original problem. Since semantic errors do not trigger runtime failures, they are difficult to detect and rectify. To address this problem, we introduce SemOPT, a semantic-guided framework for correcting LLM-based optimization models. SemOPT combines a semantic reward model that distinguishes faithful math models from plausible but incorrect ones with an adaptive correction system that applies hierarchical reward-guided search over the modeling space. Experiments on seven optimization modeling
benchmarks show that SemOPT establishes a new state of the art and achieves an average 7.6% accuracy improvement over the strongest baseline on complex
datasets.
Read the full abstract ▾
All authors Zetong Zhou, Wentao Zhang, Jingyuan Wang, Yifan Yang, Zizhuo Wang, Shixi Hu
Computer Vision
Visual Anomaly Synthesis for Model Selection in Data Scarcity
Daniel Pröll, Thomas Kraxner, Tobias Schaefer et al. (+1 more)
Defect detection systems for industrial condition monitoring can only be relied upon if they are validated, yet defective samples are rare and, for a specific asset, often nonexistent. We present a framework that synthesizes severity-graded defects on real non-defective images without any defect references for the target asset, that can be used for model selection and validation. A defect taxonomy for common failure modes is distilled from literature into prescriptive
prompts at varying defect severities. Regions of interest are cropped from in defect-free images and edited with a pre-trained image generation model ("FLUX.2 [klein]"). Color-matching and blending are employed to improve structural coherence with the original image. Generations are filtered out by a scorer and by estimated detection difficulty. Model selection experiments on MVTecAD show image AUROC choice regret over model selection can be nearly halved compared to the best fixed model chosen with access to test data. Experiments show the need for severity-graded anomaly synthesis. A case study investigates the proposed method for in-situ monitoring of Pelton turbine runners in hydropower, where real defect images are rare and expensive to collect. A PatchCorebased anomaly detection model is fit on Pelton turbine images and selected and validated using synthetic images, showing strong detection performance (94 % correct detection at optimal threshold and AUROC 0.97). The model reliably detects moderate and advanced defects, while early-stage defects remain challenging, indicating the synthetic data meaningfully stresses detector sensitivity.
Read the full abstract ▾
All authors Daniel Pröll, Thomas Kraxner, Tobias Schaefer, Sebastian Hegenbart
Robotics
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
Yifan Kang, Zihan Wang, Zhiwen Fan et al. (+1 more)
Coding
agents can now write, run, and debug programs with little human help.
Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in what order to make contact, and what the result should look like, and an
agent given only the sentence must find these details by trial and error. We introduce ENCORE, which gives the
agent a few demonstrations as evidence to read rather than as training data. A deterministic builder distills each demonstration into a pack of multi-view keyframes, gripper events, frame strips, and the full trajectory. A coding
agent studies the pack, writes a policy program against a fixed perception and action API, refines it iteratively over a few development rollouts, and freezes it before a sealed evaluation that never reveals the success signal. On LIBERO-PRO, the
agent's first program already succeeds in half of the perturbed tasks with demonstrations and in one task without them, and the frozen programs outperform the strongest prior agentic system run with the same
language model (96.3% against 89.3%). On RoboDojo tasks whose instructions leave the goal unstated, no program succeeds without demonstrations. ENCORE also runs on a real bimanual
robot, learning cube handover and cup inversion from five demonstrations each.
Read the full abstract ▾
All authors Yifan Kang, Zihan Wang, Zhiwen Fan, Bangya Liu
Artificial Intelligence
Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback
Jitin Singla, Parikshit Pareek, Pratik Jawanpuria et al. (+1 more)
Generating optimization instances that are both feasible and computationally challenging is crucial for benchmarking solvers and training learning-based optimization
algorithms. Existing non-LLM generators rely on seed instances or parameter tuning, resulting in high test-time computational cost, while existing LLM generators lack explicit hardness measures. Recent reinforcement learning methods with verifier feedback evaluate only binary correctness, which is misaligned with generating challenging problems. We note that an optimization solver reports the cost of solving at several stages of its pipeline, and leverage this to design a reward that scores both the solvability and the hardness of generated problems, measured by branch-and-bound nodes and post-cut relaxation gaps. Our key idea is a challenger-solver asymmetric self-play approach, where an LLM challenger generates progressively harder instances and the solver verifies feasibility and hardness, so no seed or training MILP instances are required. We fine-tune Gemma-4-12B and Qwen3.5-4B with GRPO and a size curriculum into OptiScribe-12B and OptiScribe-4B, which generate feasible yet challenging MILP problems from natural
language instructions. On capacitated facility location and max-cut, OptiScribe-12B raises median SCIP search nodes by 1.7-5x and post-cut gaps by 1.1-1.7x over its base model and improves the feasibility rate on facility location by 9-19 points, while OptiScribe-4B raises median nodes by up to 15.6x. The problems cover a wider difficulty range than public
benchmarks of the same size, follow instructions on density and difficulty, and can tune solver settings for families that public libraries lack. These results indicate that optimization-specific rewards, used in self-play mode, can teach LLMs to generate high-difficulty optimization
benchmarks. We will release our code and models publicly on acceptance.
Read the full abstract ▾
All authors Jitin Singla, Parikshit Pareek, Pratik Jawanpuria, Parag Singla
Artificial Intelligence
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
Zhimin Wang, Meiyuan Zhu, Duo Wu et al. (+8 more)
Vision-
Language Navigation (VLN) requires
agents to continuously ground task progress from long-horizon instructions and partial
egocentric observations. Existing VLM-based
navigation agents typically reason only over available observations and may remain confident even when task-relevant evidence is missing. For example, an
agent may confidently proceed forward and get lost even though the landmark indicating the next turn lies outside its current field of view. We term this failure mode Progress Myopia: the
agent fails to recognize unreliable progress grounding and continues acting on insufficient evidence. To address it, we propose SeekVLN, an evidence-seeking framework that couples semantic progress
reasoning with active acquisition of task-relevant observations. SeekVLN is trained in two stages: First, Future-guided Reverse Generation (FRG) uses future expert actions to augment offline expert trajectories with supplementary views and evidence annotations. Supervised fine-tuning on these trajectories establishes a prior for evidence seeking and progress
reasoning without additional expert interaction. However, imitation alone does not reveal whether seeking improves subsequent
navigation. We therefore introduce Counterfactual Contrastive Policy Optimization (C2PO) for reinforcement fine-tuning. By comparing each evidence-seeking branch with a counterfactual direct-
navigation branch from the same state, C2PO uses a contrastive reward to assign credit to seeking decisions based on subsequent
navigation benefit. Experiments on simulated
benchmarks show that SeekVLN achieves state-of-the-art performance, improving success rate by 12.7% and 7.5% over the base model on R2R-CE and RxR-CE, respectively. Both simulated and real-world evaluations exhibit human-like evidence-seeking behaviors for more reliable progress grounding.
Read the full abstract ▾
All authors Zhimin Wang, Meiyuan Zhu, Duo Wu, Linjia Kang, Yajun Wang, Yuan Ni, Xiaohang Wang, Tianlu Pan, Jingyan Jiang, Yaowei Wang, Zhi Wang
Machine Learning
Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling
Zeyu Jia
Test-time compute scaling has emerged as a cornerstone of advanced machine
reasoning, yet performing iterative deliberation directly within continuous latent representation spaces reveals a catastrophic pathology: the Deliberation Drift Cliff. While unconstrained recurrent latent models achieve initial
reasoning gains at short horizons (K <= 4), their
reasoning collapses when extrapolated to deeper thinking steps (K >= 16), dropping by 22% to 62% across standard logical
benchmarks. We resolve the trilemma among expressivity, Lyapunov stability, and computational efficiency in test-time latent
reasoning through a 22-round empirical and theoretical investigation. We demonstrate that strictly conservative scalar potential gradient flows suppress long-range drift (cliff 3.40%) but bottleneck peak
reasoning accuracy at 32.73%, whereas unconstrained rotational flows achieve high symbolic expressivity (82.33%) but suffer a severe 36.87% drift cliff. To resolve this
geometric duality, we establish Port-
Hamiltonian Latent Deliberation (PH-LD) and propose the Direct-Gradient Pure-Tensor Helmholtz-Hodge Decomposition (DG-HHD). DG-HHD parameterizes the attracting flow as a tangent projection tensor network while orthogonally decoupling non-zero circulation (Hodge machine error 1.65e-17, contraction error 5.55e-17), eliminating runtime autograd dependencies to achieve 1.84x vector field and 2.09x RK45 rollout speedups. In a 15-arm symmetrical Pareto
benchmark, DG-HHD achieves 58.67% peak accuracy (+25.94% absolute gain over conservative HHD) and retains 35.27% at K=32. Transferred to small
language model (SLM) multi-hop causal
reasoning, DG-HHD delivers monotonic compute scaling (49.33% to 51.56%) and suppresses out-of-distribution drift (cliff -0.66%). All 30 Level 0 deterministic invariants are certified.
Read the full abstract ▾
Computer Vision
PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning
Levente Lippenszky, Hongxu Yang, Marcell Dömötör et al. (+2 more)
The development of AI systems for tumor-specific applications is limited by the scarcity of labeled data. Synthetic tumor inpainting offers a promising approach but faces challenges for prostate cancer MRI which contains high-resolution multi-sequence data. Although methods leveraging latent
diffusion models (LDMs) enable large-volume synthesis, they are prone to shortcut learning, simply reproducing the condition image created by masking the lesion region. In this work, we introduce PCaPaint, a prostate cancer inpainting method based on LDMs that explicitly addresses this failure mode. To overcome shortcut learning that compromises synthetic tumor texture, we propose a simple yet efficient conditioning strategy in which the condition image is filled with Gaussian noise, and we provide theoretical justification. In addition, we propose a novel training objective for LDM that emphasizes the error within the lesion region. Furthermore, we introduce a multi-sequence latent design, in which T2w scans and DWI&ADC scans are compressed using two separate autoencoders to preserve their distinct frequency characteristics. Extensive experiments demonstrate that the generated synthetic data improves downstream performance in prostate lesion
segmentation, patient-level classification and lesion-level detection. Furthermore, our method significantly outperforms a recent state-of-the-art LDM-based tumor inpainting method both in downstream performance and in synthetic image quality.
Read the full abstract ▾
All authors Levente Lippenszky, Hongxu Yang, Marcell Dömötör, Krisztian Koos, László Ruskó
Computer Vision
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
Yalun Wu, Bingzhou Wang, Boyang Wang et al. (+5 more)
Multi-step visual
retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate state, and deciding whether to continue searching or answer. Yet retrieving relevant evidence does not ensure its effective use throughout the
reasoning trajectory. As multi-step
reasoning progresses, redundant sources occupy context capacity needed for missing evidence, observations tied to resolved requirements or unproductive searches linger in context, and visual sources are revisited with insufficient detail for fine-grained reading. We term this loss of usable evidence over a
reasoning trajectory trajectory-level evidence utilization degradation. To address it, we propose Trajectory-Aware Evidence Coordination (TAEC), a training-free framework that coordinates evidence use around unresolved answer requirements. TAEC tracks these requirements in a shared trajectory state to guide which evidence enters the context, how accumulated
memory is retained, and at what level of detail visual evidence is examined. Under a unified evaluation protocol on ViDoSeek, SlideVQA, and MMLongBench-Doc, TAEC achieves the best overall performance against leading training-free visual RAG baselines, with the highest average accuracy across multiple proprietary
vision-
language models. These results demonstrate that aligning evidence with evolving
reasoning needs improves evidence use throughout multi-step visual RAG.
Read the full abstract ▾
All authors Yalun Wu, Bingzhou Wang, Boyang Wang, Peiying Wang, Shaojie He, Yunhan Wang, Shaozu Yuan, Jiawei Wang
Robotics
DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation
Vincenzo Pomponi, Rocco Felici, Paolo Franceschi et al. (+5 more)
Learning robust manipulation policies for diverse, long-horizon tasks from limited demonstrations remains a fundamental challenge in robotics. We present DROM, a
language-guided
diffusion framework that enables
robots to learn, represent, and compose multiple manipulation skills within a single generative policy. DROM leverages Dynamic Movement Primitives (DMPs) to augment a small set of expert demonstrations into expressive multi-skill
datasets, substantially reducing data collection while improving spatial generalization beyond the demonstrated workspace. Building upon Motion Planning
Diffusion (MPD), we extend the
diffusion architecture to support
language-conditioned multi-skill trajectory generation through cross-
attention, allowing a single model to generate skill-consistent motions for a diverse set of manipulation primitives, including orientation-sensitive behaviors that are difficult to design using conventional motion planning or hard-coded controllers. For long-horizon manipulation, a large
language model decomposes high-level operator requests into executable sequences of skills, enabling natural
language interaction and autonomous task execution. We validate DROM on a Franka Emika Panda
robot, a FANUC CRX25ia
robot, and in MuJoCo simulation across a wide range of manipulation tasks. Experimental results demonstrate that DROM outperforms Motion Planning
Diffusion and Behavior Cloning baselines, achieves robust multi-skill generalization, and composes learned skills to reliably execute long-horizon manipulation tasks from natural
language instructions using only a limited number of human demonstrations.
Datasets, simulation environments, and more at https://github.com/automation-robotics-machines/drom.
Read the full abstract ▾
All authors Vincenzo Pomponi, Rocco Felici, Paolo Franceschi, Stefano Baraldo, Oliver Avram, Loris Roveda, Luca Maria Gambardella, Anna Valente
Computer Vision
When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs
Xiang Hu, Jiazuo Yu, Lu Zhang et al. (+2 more)
Streaming
video understanding requires
Video Large
Language Models (
Video-LLMs) to reason over continuous visual streams under causal constraints. As the visual history grows, a bounded visual?processing budget requires evidence selection that balances temporal recency with query relevance. Recent-only selection excludes potentially relevant historical evidence, whereas Semantic-only
retrieval can displace useful recent context when relevance scores are ambiguous. We introduce WRWS (When to Retrieve, When to Stay), a training-free framework for uncertainty-adaptive evidence allocation. A lightweight external
vision-
language encoder scores query relevance across the observed history, while an adaptive allocation module uses the normalized
entropy of the similarity distribution as a proxy for
retrieval uncertainty. WRWS favors semantic
retrieval when relevance cues are reliable and strengthens the recency prior under uncertainty. Following a retrieve-first, encode-later pipeline, WRWS selects evidence before target-model visual encoding, such that only the selected observations are processed by the costly target
Video-LLM. Experiments across four
Video-LLM families and multiple model scales demonstrate competitive accuracy on StreamingBench and OVO-Bench. In our efficiency evaluation, WRWS reduces average
vision-to-answer time to 47.93% of the state-of-the-art method. Code will be released.
Read the full abstract ▾
All authors Xiang Hu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Huchuan Lu
Machine Learning
A Sharp Transition in Data Reconstruction under Differential Privacy
Max Cairney-Leeming, Simone Bombari and Marco Mondelli
Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising
privacy concerns and motivating defenses with guarantees that remain valid against future threats. While differential
privacy (DP) provides formal protection, choosing the
privacy budget remains a challenge: small budgets severely reduce utility, but it is hard to quantify how large the budget can be without allowing accurate reconstruction. In this work, we study informed attackers who aim to reconstruct a single $d$-dimensional training sample from a $\rho$-zero-concentrated DP model, knowing all other training data. Our main contribution is to establish a sharp transition at $\rho \asymp d$ for data reconstruction: on the one hand, we derive
entropy-based lower bounds for any private mechanism and any attack, characterizing a set of target priors for which reconstruction is information-theoretically impossible for $\rho \ll d$; on the other hand, we analyze a simple attack on private linear regression with output perturbation, showing that reconstruction is practically feasible for $\rho \gg d$. Remarkably, the transition moves to $\rho \asymp s$ for data lying in an $s$-dimensional subspace, demonstrating that the
privacy budget guaranteeing adequate protection must be assessed in terms of the effective dimension of the data. We validate our findings via experiments on synthetic data and natural images (CIFAR-10, ImageNet).
Read the full abstract ▾
Data Structures and Algorithms
Collision Detection is Instance $\widetilde{O}$ptimal Under the Birthday Threshold
Omri Ben-Eliezer, Tomer Grossman, Václav Rozhoň et al. (+1 more)
Can structural knowledge about a hash function help accelerate the (black box) detection of collisions in it? This question is fundamental to cryptography theory given the importance of collision-resistant hash functions, and in this paper we tackle it from the angle of instance optimality, an ultimate notion of beyond worst case
algorithm analysis that has gained significant traction in recent years. Instance optimality asks for a single
algorithm that, on every input, performs nearly as well as the best correct
algorithm that “knows the structure” of that specific input. Here we measure
algorithms by the number of queries they make to the hash function $f\colon [n]\to [n]$, and we say that an
algorithm “knows the structure” of the input if, in addition to query access to $f$, it has free access to an unlabeled copy $\pi^{-1}\circ f\circ\pi$ of $f$, for an unknown permutation $\pi$ on $[n]$. We prove the existence of an (almost) instance-optimal
algorithm for collision detection in the regime most interesting from a cryptographic perspective: among functions where finding a collision takes significantly less than $\sqrt{n}$ queries. Specifically, we prove the existence of a single
algorithm $A$ that, for any input $f$ in which a structure-aware
algorithm can find a collision using $q\leq O(\sqrt{n/\log n})$ queries in expectation, $A$ can find a collision in at most $O(q\log n)$ queries. The $O(\log n)$ multiplicative overhead is tight, matching a lower bound of Ben-Eliezer, Grossman, and Naor [ICALP'25], and partially resolving their main open question. Our result implies, in particular, that it is impossible for a cryptographic designer to plant purely structural
backdoors for collision finding (for this unlabeled notion of structure): whatever collisions the designer's secret knowledge finds, the public can find with a multiplicative overhead of $O(\log n)$.
Read the full abstract ▾
All authors Omri Ben-Eliezer, Tomer Grossman, Václav Rozhoň, Jakub Tětek
Computer Vision
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
Li Pang, Xinqiao Wu, Jing Yao et al. (+5 more)
Hyperspectral remote sensing provides dense spectral measurements that are indispensable for material-level Earth observation, yet the construction of a general-purpose hyperspectral foundation model remains difficult. Two bottlenecks are especially limiting. First, large hyperspectral corpora rarely provide high spatial resolution together with reliable dense annotations. Second, many hyperspectral models are still trained almost from scratch, so the
geometric and interactive priors learned by modern
vision foundation models are not fully reused. To alleviate these issues, we \highlight{present} HyperSAM, a promptable hyperspectral foundation model that couples a data-centric hyperspectral synthesis pipeline with a spectral adaptation architecture based on Segment Anything Model 3 (SAM3). On the data side, HyperSAM synthesizes full-spectrum hyperspectral cubes from high-resolution SpaceNet multispectral imagery through a physics-informed abundance-transfer generator, while SAM3-derived pseudo-masks provide object-centric supervision. On the model side, the latest implementation uses a frozen SAM3 RGB image branch, a trainable hyperspectral side encoder initialized from the RGB
vision transformer (ViT), ControlNet-style zero-initialized feature injection, and a lightweight mixture-of-experts mask refiner. To enhance training robustness against noisy pseudo-labels, Cross-modal Sample Selection (CromSS)-style confidence selection is incorporated for noisy-label weighting. Extensive experiments show that HyperSAM obtains strong generalization on diverse hyperspectral tasks (e.g., classification, anomaly detection, change detection, target detection, and airborne oil-spill mapping) and that high-quality synthetic hyperspectral data can be more effective than simply scaling noisy hyperspectral supervision.
Read the full abstract ▾
All authors Li Pang, Xinqiao Wu, Jing Yao, Pedram Ghamisi, Jun Zhou, Zhengchao Chen, Deyu Meng, Xiangyong Cao
Computer Vision
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation
Jer Pelhan, Alan Lukezic and Matej Kristan
General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding boxes and surrogate training, and struggles with non-rigid objects, crowded scenes, and distractors. We introduce UGO, a unified GMOT tracker that pairs a pretrained exemplar-conditioned detection head with an instance-propagation head in a common architecture. A novel training-free, energy-minimization consolidation method converts overlapping proposals into exclusive pixel-wise masks and detections, resolving over-
segmentation, duplicates, and conflicts. A hierarchical
memory spanning global and instance levels improves recall and per-instance
segmentation accuracy using a new
memory management protocol. UGO sets a new state-of-the-art on GMOT
benchmarks and
video object counting, and is competitive with specialist MOT methods, establishing a strong paradigm for unified, open-category multi-object tracking.
Read the full abstract ▾
Information Theory
Rotatable Antenna-Enabled Space-Air-Ground Integrated Networks: Opportunities and Challenges
Yanhua Tan, Beixiong Zheng, Tiantian Ma et al. (+6 more)
Space-air-ground integrated networks (SAGINs) are expected to support ubiquitous three-dimensional (3D) communication and sensing services in future sixth-generation (6G) wireless networks. However, heterogeneous mobility and service requirements across the space, air, and ground segments challenge fixed-boresight or fixed-sector
antennas in supporting wide-area coverage, maintaining directional
alignment over time-varying communication links, and flexibly adjusting observation directions for sensing tasks. To address these limitations, non-fixed flexible
antenna architectures, such as fluid
antenna system (FAS), movable
antenna (MA), and pinching
antenna, have garnered significant interest in recent years. Among them, rotatable
antenna (RA) technology has emerged as a promising solution by enabling mechanical or electronic boresight adjustment while keeping the
antenna positions fixed. This article investigates the roles of RA technology in enabling communication and sensing in SAGINs. Specifically, we first explain how RA boresight control complements platform mobility and supports wide-area coverage, dynamic directional transmission, cross-segment cooperative operation, and cooperative sensing. We then discuss the main design challenges, potential approaches, and future research directions, including channel acquisition and predictive tracking, joint orientation control and access/handover coordination, cross-segment coordination and resource management, as well as deployment tradeoffs and practical implementation. Finally, an RA array prototype and two representative simulation studies are presented to illustrate the feasibility and potential performance gains of RA-enabled SAGINs.
Read the full abstract ▾
All authors Yanhua Tan, Beixiong Zheng, Tiantian Ma, Qingjie Wu, Lipeng Zhu, Wenyan Ma, Cheng-Xiang Wang, Robert Schober, Rui Zhang
Logic in Computer Science
A Rank-Preserving Gaifman Normal Form for First-Order Logic on Weighted Structures
Steffen van Bergerem, Martin Grohe, Charlotte Lenz et al. (+1 more)
We prove a rank-preserving version of Gaifman's
Theorem. Compared to earlier rank-preserving locality
theorems (in particular, [Grohe, Kreutzer, Siebertz, JACM 2017]), our
theorem is much simpler and yields formulas in exactly the same normal form as Gaifman's original
theorem. Furthermore, it holds not only for first-order logic, but also for first-order logic with modulo-counting quantifiers and, more generally, for the first-order logic on weighted structures ngFOW+ that is introduced in this article. As an application of our
theorem, we give a simplified proof of the algorithmic meta-
theorem of [Grohe, Kreutzer, Siebertz, JACM 2017] stating that first-order properties of nowhere dense structures can be decided in almost-linear time. Our locality
theorem for the weight logic ngFOW+ can be seen as an essential step toward such a meta-
theorem for this logic.
Read the full abstract ▾
All authors Steffen van Bergerem, Martin Grohe, Charlotte Lenz, Nicole Schweikardt
Robotics
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Sohyun Lee, Yoonjae Baek, Jaesang Won et al. (+5 more)
Vision-
language-action (VLA) policies often fail when a
robot's executed motion deviates from their commanded action. Such execution errors arise from the
robot's mechanics and operating conditions, such as wear and payload changes. We propose self-compensating VLA, a deployment-time adaptation method that enables a VLA policy to pre-compensate for the
robot's execution errors when generating commands. Without task rewards or labels, it updates the policy online using the residual between the action commanded by a VLA and the motion executed by the
robot. To stress-test VLA robustness across execution conditions that are impractical to cover with physical
robots alone, we introduce RoboStress, a controlled simulation
benchmark. It combines established joint-level models of friction, backlash, compliance, and
gravity-compensation error into seven deployment scenarios whose execution errors depend on the
robot's state and motion history. On RoboStress, self-compensating VLA achieves higher average task success than both the base policies and methods that build in robustness during training. On two physical
robot arms with different usage histories, it raises the average task success rate by more than 30 percentage points on each arm, and the gains extend to objects not seen in the task demonstrations.
Read the full abstract ▾
All authors Sohyun Lee, Yoonjae Baek, Jaesang Won, Jinnyeong Kim, Kang Hyunwoo, Seung-Hwan Baek, Ivan Laptev, Suha Kwak
Computer Vision
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
Shenghan Chen, Yiming Liu, Zhipeng Deng et al. (+6 more)
Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, representation learning, or data augmentation, but the underlying cause of tail class degradation is still insufficiently explored. In this paper, we find that standard long-tailed training induces background-biased representation and optimization: tail classes suffer larger background distribution shifts and become increasingly driven by background gradients. This reveals that tail degradation is not merely caused by insufficient samples, but also by the learning of irrelevant background features. To tackle this issue, we propose Object-Focused Background Debiasing (OFBD), a framework that mitigates background bias from both distribution and optimization perspectives. Specifically, Foreground-guided CutMix preserves target-related foregrounds while diversifying complementary backgrounds, and Background-guided Feature Rectification suppresses background-biased features without learnable parameters or additional training. Extensive experiments show that our method improves overall accuracy, achieves significant tail-class gains, and can serve as a plug-in for mainstream long-tailed methods without external data or pretrained recognition models. The code is available at: https://ofbd-neurips2026-longtail-learning.github.io/
Read the full abstract ▾
All authors Shenghan Chen, Yiming Liu, Zhipeng Deng, Haolin Wang, Jiale Zhou, Zhijian Wu, Xiankai Lu, Yafei Ou, Yefeng Zheng
Computer Vision
The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators
Thomas Deixelberger and Markus Steinberger
Clearing fog, rain or snow from footage, or turning renders into photographs, must remove the source domain and keep the scene. Unpaired translators carry it through because their generator sees the source appearance (pixels, a near-invertible latent or a control map) and keeps it. A DINO feature map fixes what is in the scene and carries weather, lighting and rendering style as a residue of 13 to 14% of the feature norm. We propose the Representation Feature Adapter (RFA), a 2.9M-parameter network that moves this residue. We train only the adapter and its discriminators; the encoder and a feature-conditioned decoder, trained once for all conditions, stay frozen. Against CycleGAN-Turbo it is ahead on both metrics on fog and on KID on night, and level within noise on snow, rain and haze. On sim-to-real it leads REGEN and HyPER-GAN on both metrics. Only the RFA removes the rain while keeping the scene. The removal costs scene structure: CycleGAN-Turbo keeps more on every condition but fog. On VAE latents the identical adapter collapses to the identity, and decoders from other groups that never saw it render its output. The RFA has about 160 times fewer trainable parameters than CycleGAN-Turbo and under a fifth of its per-condition training time.
Read the full abstract ▾
Human-Computer Interaction
EntityWeaver: Visual Exploration and Curation of Named-Entity Relationships in Document Collections
Uroš Šmajdek and Ciril Bohak
We present an interactive visualization system for exploring named entities and their relationships across document collections, with a strong focus on handling uncertainty and supporting both distant and close reading. The system is built around a graph that links documents, entity mentions, and entities. Uncertainty from mention-to-entity linking is included directly in this graph, so users can see where connections are strong, weak, or ambiguous. A transfer-function control, inspired by approaches in scientific visualization, allows users to adjust how this uncertainty is displayed, making it easy to tune the visualization for different
datasets and research questions. The system also provides direct access to the full source texts in a coordinated view, enabling quick context checks, resolving ambiguous cases, and correcting digitization errors. Exploration is further supported through a multi-stage filter query builder, mini-map
navigation for large graphs, and export options for downstream analysis. By combining uncertainty-aware graph visualization with direct interaction in the source texts, the system provides a unified workflow that supports both large-scale pattern discovery and curation of named-entity-based document collections. The design choices were supported by the domain experts, who were also involved in the initial system evaluation.
Read the full abstract ▾
Artificial Intelligence
Solving Without Stopping: On-Policy Distillation at Small Scale
Hongyang Li, Yiming Zhu, Xiao Li et al. (+3 more)
On-policy
distillation, where a student learns from a stronger teacher's feedback on its own outputs, is a common way to pass
reasoning to smaller models. We analyze what it transfers at small scale, distilling Qwen3-8B into Qwen3 4B, 1.7B and 0.6B students, in thinking mode (reason at length, then end the
reasoning and answer) and, for comparison, in non-thinking mode (no separate
reasoning phase). Long
reasoning needs two abilities, solving a problem and knowing when it is solved, and we find that
distillation transfers the first, but in thinking mode not the second. Solving improves at every size, up to two ceilings, which we measure comprehensively across both modes and all student sizes: a student's single attempt never exceeds what it could already reach in many attempts before training, and the smaller the student, the further it stays below the teacher. Stopping is where the modes part. In non-thinking mode every student keeps stopping; in thinking mode students stop ending their
reasoning early in training, and the smaller the student, the less of this ability survives: the teacher signals a stop almost only where a student already ends its
reasoning, so
distillation teaches no new stops; it only keeps the student's existing stops that land on a right answer, and a weak student has few such stops. The smallest students often reach the right value but do not commit to it: they either rarely mark it or mark it and write past it. Together, these results describe how small students behave under on-policy
distillation, and a diagnostic that separates answer marking, correctness and stopping.
Read the full abstract ▾
All authors Hongyang Li, Yiming Zhu, Xiao Li, Caesar Wu, Said Mammar, Pascal Bouvry
Artificial Intelligence
VISTA: Value-Informed Event Appraisal for Multimodal Emotion Conflict
Jiale Dai, Liuxian Ma, Xiaoke Niu et al. (+5 more)
Conflicting emotional cues can be individually valid: a subdued voice may reflect a blocked goal while a smile satisfies a social obligation. Their interpretation depends on what the event means to the person. We introduce VISTA (Value-Informed Semantic Trust Arbitration), a learned seven-field appraisal interface that conditions modality arbitration on concerns, event relations, and expression conditions while retaining a joint-evidence residual. A log-odds decomposition separates
emotion expectation from cue diagnosticity, motivating an interface that lets appraisal change how evidence is interpreted. With a shared Qwen2.5-Omni-7B backbone and matched training examples and steps, VISTA reaches 64.5% conflict accuracy on CA-MER, improving on modality gating by 2.5 percentage points on conflict and 0.2 on consistency. Shuffling appraisal across scenes or removing its decision connection reduces this benefit. A common frozen-backbone probe reaches 0.600 macro CCC for appraisal readout, compared with 0.505 for
emotion-only fine-tuning. Evaluations across five
benchmarks connect recognition under increasing conflict with appraisal readout and downstream decision use. Together, the analyses and experiments support scene-specific appraisal as an intermediate representation that helps interpret conflicting emotional evidence.
Read the full abstract ▾
All authors Jiale Dai, Liuxian Ma, Xiaoke Niu, Wenjing Zhang, Huiying Zhao, Zhaoxiang Liu, Shiguo Lian, Guojie Song
Machine Learning
Parallel Tempering for Diffusion-Based Combinatorial Optimization
Arman Mielke, Uwe Bauknecht, Thilo Strauss et al. (+1 more)
Discrete
diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-quality solutions. A common inference-time approach is to generate multiple candidate solutions independently and return the best-performing sample, improving solution quality at the expense of an increase in computational cost. In this work, we introduce PT-Denoise, an inference-time procedure that allows these concurrent denoising trajectories to interact through parallel tempering, without requiring retraining or fine-tuning of the underlying denoiser. Our method assigns a temperature to each
diffusion process and allows processes to swap temperatures based on their relative performance. This dynamically reallocates promising, low-energy trajectories to colder, more concentrated sampling regimes while allowing higher-energy states to escape local minima through randomized exploration. Experiments on canonical graph-structured CO problems show that our approach consistently improves the quality of the best solution found, while only adding minimal computational overhead.
Read the full abstract ▾
All authors Arman Mielke, Uwe Bauknecht, Thilo Strauss, Mathias Niepert