420434 results (page 8 of 16818)
-
Calibration-Aware Policy Optimization for Reasoning LLMs
Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity than correct ones, degrading relative calibration as described by the Area Under the Curve (AUC). Existing approaches either yield limited improvements in calibration or sacrifice gains in reasoning accuracy. We first prove that this degradation in GRP…
-
GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
Multimodal large language models (MLLMs) have exhibited remarkable performance in various visual tasks, yet still struggle with spatial reasoning. Recent efforts mitigate this by injecting geometric features from 3D foundation models, but rely on static single-layer extractions. We identify that such an approach induces a task misalignment bias: the geometric features naturally evolve towards 3D p…
-
A Comparison of Reinforcement Learning and Optimal Control Methods for Path Planning
Path-planning for autonomous vehicles in threat-laden environments is a fundamental challenge. While traditional optimal control methods can find ideal paths, the computational time is often too slow for real-time decision-making. To solve this challenge, we propose a method based on Deep Deterministic Policy Gradient (DDPG) and model the threat as a simple, circular `no-go' zone. A mission failur…
-
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based RL methods mitigate sparsity by injecting partial solutions or abstract templates, yet they typically scale guidance by adding more tokens, which introduce redundancy, inconsistency, and extra training overhead. We propose \textbf{KnowRL} (Knowledge…
-
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Training embodied AI agents depends critically on the visual fidelity of simulation environments and the ability to model dynamic humans. Current simulators rely on mesh-based rasterization with limited visual realism, and their support for dynamic human avatars, where available, is constrained to mesh representations, hindering agent generalization to human-populated real-world scenarios. We pres…
-
Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments
High-quality global illumination (GI) in real-time rendering is commonly achieved using precomputed lighting techniques, with lightmap as the standard choice. To support GI for static objects in dynamic lighting environments, multiple lightmaps at different lighting conditions need to be precomputed, which incurs substantial storage and memory overhead. To overcome this limitation, we propose Ne…
-
GraphTide: Augmenting Knowledge-Intensive Text with Progressive Nested Graph
Knowledge-intensive text usually contains fruitful entities and complex relationships, such as academic articles and scientific exposition. Reading and comprehending such texts often demands considerable time and mental effort to track the relationships between entities. To reduce the burden, we present GraphTide, a visualization technique that progressively constructs nested entity-relationship g…
-
Efficient Semantic Image Communication for Traffic Monitoring at the Edge
Many visual monitoring systems operate under strict communication constraints, where transmitting full-resolution images is impractical and often unnecessary. In such settings, visual data is often used for object presence, spatial relationships, and scene context rather than exact pixel fidelity. This paper presents two semantic image communication pipelines for traffic monitoring, MMSD and SAMR,…
-
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on ground-truth states sampled from the forward noising process; once inference deviates from these ideal states, subsequent denoising relies on out-of-distributio…
-
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
The rapid evolution of Vision-Language Models (VLMs) has catalyzed unprecedented capabilities in artificial intelligence; however, this continuous modal expansion has inadvertently exposed a vastly broadened and unconstrained adversarial attack surface. Current multimodal jailbreak strategies primarily focus on surface-level pixel perturbations and typographic attacks or harmful images; however, t…
-
DeepTest Tool Competition 2026: Benchmarking an LLM-Based Automotive Assistant
This report summarizes the results of the first edition of the Large Language Model (LLM) Testing competition, held as part of the DeepTest workshop at ICSE 2026. Four tools competed in benchmarking an LLM-based car manual information retrieval application, with the objective of identifying user inputs for which the system fails to appropriately mention warnings contained in the manual. The testin…
-
Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. However, the effectiveness of RAG depends not only on the design of the retriever and the capacity of the underlying model, but also on how retrieved evidence is structured and aligned with the query. Existing RAG approaches typically retrieve and conc…
-
Metal enrichment in the galaxy group IC 1262
We present a new metal enrichment analysis of a unique galaxy group IC 1262 using archival Chandra and GMRT observations, focusing on metal transport via radio jet, sloshing cold fronts, and shock front. This group shows two sloshing cold fronts along the east and north-west direction which is nearly orthogonal to the north - south orientated radio jet. We report discontinuities in the metallicity…
-
LLM-Guided Prompt Evolution for Password Guessing
Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credential leaks. Automated password guessing is a key tool for stress-testing password policies and modeling attacker behavior. This paper applies LLM-driven evolutionary computation to automatically optimize prompts for the LLM password guessing framework…
-
Spatial-Spectral Adaptive Fidelity and Noise Prior Reduction Guided Hyperspectral Image Denoising
The core challenge of hyperspectral image denoising is striking the right balance between data fidelity and noise prior modeling. Most existing methods place too much emphasis on the intrinsic priors of the image while overlooking diverse noise assumptions and the dynamic trade-off between fidelity and priors. To address these issues, we propose a denoising framework that integrates noise prior re…
-
Unveiling Dominant Toroidal Magnetic Fields in a Protostellar Outflow
Magnetic fields play a fundamental role in the formation of protostellar winds. In the magneto-centrifugal models, poloidal magnetic fields launch winds from accretion disks, and fast-rotating gas twists the fields into toroidal geometry that collimates and accelerates winds through magnetic hoop stress. However, toroidal fields in protostellar winds remain observationally unresolved. Here we repo…
-
KumoRFM-2: Scaling Foundation Models for Relational Learning
We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fine-tuning and is applicable to a wide range of predictive tasks. In contrast to tabular foundation models, KumoRFM-2 natively operates on relational data, processing one or more connected tables simultaneously without manual table flattening or targe…
-
ELoG-GS: Dual-Branch Gaussian Splatting with Luminance-Guided Enhancement for Extreme Low-light 3D Reconstruction
This paper presents our approach to the NTIRE 2026 3D Restoration and Reconstruction Challenge (Track 1), which focuses on reconstructing high-quality 3D representations from degraded multi-view inputs. The challenge involves recovering geometrically consistent and photorealistic 3D scenes in extreme low-light environments. To address this task, we propose Extreme Low-light Optimized Gaussian Spla…
-
Machine Learning-Based Real-Time Detection of Compensatory Trunk Movements Using Trunk-Wrist Inertial Measurement Units
Compensatory trunk movements (CTMs) are commonly observed after stroke and can lead to maladaptive movement patterns, limiting targeted training of affected structures. Objective, continuous detection of CTMs during therapy and activities of daily living remains challenging due to the typically complex measurements setups required, as well as limited applicability for real-time use. This study inv…
-
Impact of the SNe Ia Magnitude Transition at 20 Mpc on Cosmological Parameter Estimation
We investigate the impact of a late-time transition in the standardized absolute magnitude $M$ on the best-fit values of cosmological parameters using the Pantheon+ dataset. Extending previous analyses which focused on flat $Λ$CDM, we examine this transition within flat $Λ$CDM, wCDM, and CPL cosmologies, as well as a model-independent cosmographic expansion, employing both frequentist ($χ^2$ minim…
-
Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models
Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations. Existing mitigation methods typically rely on training, input modification, auxiliary guidance, or additional decoding procedures, while largely overlooking a more fundamental challenge. During generation, Video-LLMs tend to over-rely on a limited p…
-
Primordial Black Holes Formation Beyond the Standard Cosmic QCD Transition
We review the role of primordial black holes (PBHs) for illuminating the dark ages of the cosmological evolution and as dark matter (DM) candidates. We elucidate the role of phase transitions for primordial black hole formation in the early Universe and focus our attention on the cosmological QCD phase transition within a recent microscopical model. We explore the impact of physics beyond the Stan…
-
PDF-GS: Progressive Distractor Filtering for Robust 3D Gaussian Splatting
Recent advances in 3D Gaussian Splatting (3DGS) have enabled impressive real-time photorealistic rendering. However, conventional training pipelines inherently assume full multi-view consistency among input images, which makes them sensitive to distractors that violate this assumption and cause visual artifacts. In this work, we revisit an underexplored aspect of 3DGS: its inherent ability to supp…
-
EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts
Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EEG-based paradigms, one promising approach is to leverage their hierarchical structures, as recent st…
-
StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation
This paper introduces StructDiff, a generative framework based on a single-scale diffusion model for single-image generation. Single-image generation aims to synthesize diverse samples with similar visual content to the source image by capturing its internal statistics, without relying on external data. However, existing methods often struggle to preserve the structural layout, especially for imag…