category.学术arXiv cs.LG (机器学习)
arXiv:2606.11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded. At race speeds, where collisions are instantaneous and irreversible, any safety mechanism
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11314v1 Announce Type: new Abstract: We introduce TRON, a rendering framework that combines 3D Gaussian ray tracing with neural rendering to enable realistic and controllable rendering of real-world 3D scenes under novel lighting, dynamic object motion, object insertion, and material editing. Prior approaches that rely solely on physically based rendering (PBR) of Gaussian representatio
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11290v1 Announce Type: new Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per que
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11262v1 Announce Type: new Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference. A common hypothesis is that interference during adapter composition arises from overlap in linear parameter updates, suggesting that enforcing orthogonality or directional independence should i
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11258v1 Announce Type: new Abstract: Gradient-based inversion of reaction-diffusion systems is typically approached via surrogate models or physics-informed neural networks (PINNs), while the most direct route, backpropagation through the PDE's structure itself, has largely been avoided. We pursue this direct route as a diagnostic probe, backpropagating a steady-state loss through unrol
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11349v1 Announce Type: new Abstract: In hierarchical reasoning, failures often originate at intermediate decision points where the agent commits to a wrong branch without recognizing that it lacks critical information. Rather than treating clarification as an external uncertainty trigger, we propose ACTION-RATING, a formulation that places it inside the agent's action space on a shared
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.12018v1 Announce Type: new Abstract: We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key feature of our approach is that both the training and inference phases are augmented via knowledge distillation. Within this architecture, multi-modal data pertinent to social
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11320v1 Announce Type: new Abstract: In this paper, we present a novel set of related models for semantic segmentation of node-link diagrams. These diagrams are frequently used to represent mathematical graphs, relationships between concepts, and flowcharts. Such diagrams are difficult to access non-visually; while some assistive interfaces have been designed for node-link diagrams, the
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11207v1 Announce Type: new Abstract: We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference targets including purchase intent, customer segmentation, and product affinity through a shared element library. Unlike conventional end-to-end predictors that optimise solely for accuracy, SemantiClean
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11382v1 Announce Type: new Abstract: Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds. However, the computational burden to develop and deploy state-of-the-art models continuously increases, limiting their scalability. Most large-scale models are unimodal in nature and overlook the potential to leverage complementa
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11235v1 Announce Type: new Abstract: A key step in knowledge discovery is the evaluation of data mining results. In several applications, including pattern mining, graph analysis, and others, this step includes the evaluation of the statistical significance of the results, to avoid spurious discoveries due only to noise or random fluctuations in the data. While specialized procedures ha
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11251v1 Announce Type: new Abstract: Many multivariate dynamical systems are observed only through trajectories, leaving the mechanisms governing their joint dynamics hidden. Existing approaches can impose interpretable dynamics or learn flexible state transitions, yet the resulting interaction structure is typically either specified in advance or left implicit within the learned dynami
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11326v1 Announce Type: new Abstract: Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation from image streams. However, their reliance on visible-light appearance makes them vulnerable in dark and low-visibility environments, where RGB cues are severely degraded and geometric evidence becomes
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11268v1 Announce Type: new Abstract: Understanding and forecasting lake dynamics is critical for monitoring water quality and ecosystem health across lakes and reservoirs. While machine learning methods have been recently applied to ecological time-series data, existing works assume regular sampling in time and depth, and struggle to generalize across lakes with heterogeneous variables,
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11247v1 Announce Type: new Abstract: Generative models are increasingly used to propose designs, data, and control actions for physical systems, yet many such systems are governed by hard physical constraints rather than by perceptual plausibility. Semiconductor manufacturing provides a demanding test case: generated masks, layouts, synthetic defect data, and process recipes must obey l
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11391v1 Announce Type: new Abstract: Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recursive structures. Conversely, Vector Symbolic Architectures maintain constant dimensionality but sacrifice capacity and fidelity due to noisy compression via superposition. I
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11255v1 Announce Type: new Abstract: Bernstein--Schur kernels are products of a finite-feature kernel (one with an explicit finite-dimensional feature map) and a completely monotone shift-invariant kernel: nonstationary kernels that fall between the shift-invariant and dot-product templates random features usually exploit, so in general neither Bochner sampling nor polynomial sketching
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11243v1 Announce Type: new Abstract: De novo protein generation has transformative potential in therapeutic design, enzyme engineering, and synthetic biology. While diffusion-based and flow matching approaches have achieved progress, they typically operate at single resolution and lack mechanisms for incorporating functional constraints. We introduce ProHiFlo, a hierarchical flow matchi
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11319v1 Announce Type: new Abstract: Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability. Here we examine attribute noise: learning from corrupted inputs while keeping the labels intact, a setting that has received considerably less analytical attention than its label-noise counterpart
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization in reinforcement learning and LLM post-training. This raises a basic robustness question, crucial to reproducibility and reliability: how sensitive are MD dynamics to their inputs? We focus on initia
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11474v1 Announce Type: new Abstract: In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems. RL controllers can quickly control high-dimensional systems within the training distribution, but their performance can degrade when time-varying dynamics produce unseen observations. We consid
6月11日 04:00
category.学术arXiv cs.LG (机器学习)
arXiv:2606.11473v1 Announce Type: new Abstract: Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11851v1 Announce Type: new Abstract: Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions. Across multiple rounds of exploration, a discovery agent must decide which phenomena warrant investigation while avoiding overinterpretation, where emerging claims exceed the evidential scope of the analyses supporting them. This creates an evidenc
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11573v1 Announce Type: new Abstract: Radar-camera BEV perception often suffers from degraded performance when evaluated across datasets, as changes in driving scenes, sensor configurations, and environmental conditions can alter both the input observations and the internal fused representations. This work studies this issue from the perspective of source-domain variation modeling, aimin
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11477v1 Announce Type: new Abstract: Correcting handwritten exams by hand is time-consuming and error-prone, particularly for large cohorts, while fully digital exams tend to force a didactic narrowing towards closed question formats. A practical middle ground keeps paper-based, problem-oriented tasks but records the assessment-relevant answers as single capital letters in a table that
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11572v1 Announce Type: new Abstract: Transfer learning from large-scale RGB foundation models to infrared (IR) imagery through knowledge distillation (KD) remains challenging due to fundamental differences in image formation physics. We investigate the spectral structure of the RGB--IR modality gap and observe that feature divergence is not uniform across spatial frequencies: low-freque
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11466v1 Announce Type: new Abstract: Point cloud semantic segmentation requires architectures that capture both fine-grained local geometry and broad global scene structure. Transformer-based networks have demonstrated strong performance by focusing on detailed local feature aggregation; however, global context is conveyed primarily through skip connections across encoder-decoder stages
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11546v1 Announce Type: new Abstract: Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-
6月11日 04:00
category.学术arXiv cs.CL (自然语言处理)
arXiv:2606.11202v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in applications for global multilingual users, yet safety training remains concentrated in dominant languages and has not progressed in parallel with multilingual capability, creating exploitable gaps for jailbreak attacks. Current jailbreak defenses are largely developed and evaluated in dominan
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11576v1 Announce Type: new Abstract: Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains. We view this cost through two coupled axes: Visual Context Scaling (VCS), which controls how much visual evidence is passed to the languag
6月11日 04:00
category.学术arXiv cs.CL (自然语言处理)
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic evaluation across social sciences remains limited. Existing evaluation benchmarks are insufficient, either small or conflate agent performance with problems in the reproduction materials themselves, such
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11804v1 Announce Type: new Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization determines which information is retained and passed to subsequent learning or decision modules. Therefore, adversarial perturbations to the summarization process can compromise trustworthy AI in an ups
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11874v1 Announce Type: new Abstract: With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs has become essential for data-driven evaluation. In this paper, we propose AutoMine, a robust self-refining scenario mining method based on LLMs and VLMs. AutoMine uses semantics-preserving prompt augme
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11578v1 Announce Type: new Abstract: Contactless body measurement technologies are becoming increasingly significant for smart health monitoring, digital health applications, and remote patient assessment. Traditional anthropometric measurements typically necessitate physical contact and trained personnel, which may constrain scalability in remote healthcare settings. In this study, we
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based approaches improve ToM reasoning through observable-event filtering or temporal belief chains, without explicitly modeling nested beliefs. We introduce RecToM, an inference-time
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11769v1 Announce Type: new Abstract: The European AI Act is the first comprehensive regulation of artificial intelligence (AI), setting out extensive obligations, particularly for so-called high-risk and general-purpose AI systems. A key distinguishing feature of AI systems under the AI Act is the capability to infer. Since the AI Act does not clearly define what inference is, there is
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11770v1 Announce Type: new Abstract: Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions. Current studies often leave intermediate states unverified and treat state transitions as implicit processes, which limits reliability in multi-hop spatial reasoning. To a
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11615v1 Announce Type: new Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To address this challenge, we propose Adv-TGD, a generative adversarial attack framework that synthesizes photorealistic faces capable of impersonating target identities and deceiving face recognition systems
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11637v1 Announce Type: new Abstract: Touch is a key modality for embodied agents to understand the physical world. Although recent work has incorporated tactile signals into language systems for tactile commonsense reasoning, scaling such systems to realistic open-world settings remains challenging due to two key bottlenecks: (1) current tactile reasoning datasets remain limited in form
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11601v1 Announce Type: new Abstract: In fringe projection profilometry (FPP), depth is commonly recovered by fitting a phase-to-depth relation independently at each camera pixel. Although such pixel-wise calibration achieves high local accuracy, neighboring pixels can acquire markedly different calibration functions even when they observe the same smooth surface, producing spatially inc
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11634v1 Announce Type: new Abstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length. To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathemat
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11602v1 Announce Type: new Abstract: Audio-visual Generalized Zero-shot Learning (AV-GZSL) is a challenging task that aims to classify both seen and unseen objects or scenes by integrating data from audio and visual modalities. Recent studies primarily focus on fusing or aligning audio and visual features to generate more informative audio-visual embeddings. Also, aligning the audio-vis
6月11日 04:00
category.学术arXiv cs.CL (自然语言处理)
arXiv:2606.11220v1 Announce Type: new Abstract: Forecasting human life outcomes is important to gain insights into how individuals attain long and healthy lives. Conventional statistical approaches yield limited accuracy, potentially due to discarding the sequential structure of the life course. Modern methods such as transformer architectures require large scale training data that most longitudin
6月11日 04:00
category.学术arXiv cs.CV (计算机视觉)
arXiv:2606.11606v1 Announce Type: new Abstract: Frozen vision-transformer (ViT) foundation-model embeddings increasingly serve as the substrate for downstream chest-radiography (CXR) pipelines, yet where small-scale, low-contrast signal is retained or lost in the frozen forward pass has not been systematically quantified across architectures, pretraining domains, and objectives. We probed five fro
6月11日 04:00
category.学术arXiv cs.CL (自然语言处理)
arXiv:2606.11222v1 Announce Type: new Abstract: How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metrics such as BERTScore compare two texts rather than characterizing one. We develop a geometric framework that measures semantic content from the structure of a text's sentence embeddings. The framework
6月11日 04:00
category.学术arXiv cs.CL (自然语言处理)
arXiv:2606.11257v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation. Running them entirely on-device benefits privacy, latency, and offline use, but the energy cost of CPU inference is a major barrier. We present what is, to our knowledge, the first end-to-end RAG
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11662v1 Announce Type: new Abstract: Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge is deciding how to search when several directions look plausible but only some will later lead to reliable evidence. If an agent greedily follows the current best-looking direction, it may keep exten
6月11日 04:00
category.学术arXiv cs.AI
arXiv:2606.11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms. However, existing approaches ei
6月11日 04:00