Knowledge catalogue
arXiv:2601.03027v3 Announce Type: replace Abstract: Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce halluc
arXiv:2603.28942v3 Announce Type: replace Abstract: The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propens
arXiv:2604.13262v1 Announce Type: new Abstract: In medical image segmentation, uncertainty estimates are often reported but rarely used to guide decisions. We study the missing step: how uncertainty m
arXiv:2604.13602v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multi
arXiv:2508.00222v5 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs
arXiv:2603.22126v3 Announce Type: replace Abstract: Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high
arXiv:2604.13525v1 Announce Type: cross Abstract: The robust low-rank tensor completion problem addresses the challenge of recovering corrupted high-dimensional tensor data with missing entries, outli
arXiv:2604.13833v1 Announce Type: new Abstract: Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone.
arXiv:2604.13817v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable capabilities in dialogue generation and reasoning, yet their effectiveness in eliciting user-known bu
arXiv:2510.18165v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm, offering inhere
arXiv:2204.13635v2 Announce Type: replace Abstract: Depth completion involves recovering a dense depth map from a sparse map and an RGB image. Recent approaches focus on utilizing color images as guid
arXiv:2604.13515v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) is a common post-training recipe. We conduct a controlled ablation ov
arXiv:2604.13405v1 Announce Type: new Abstract: Singular configurations cause loss of task-space mobility, unbounded joint velocities, and solver divergence in inverse kinematics (IK) for serial manip
arXiv:2604.13710v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) exhibit strong reasoning and world knowledge, yet adapting them for retrieval remains challenging. Existing app
arXiv:2604.13581v1 Announce Type: new Abstract: Accurately reconstructing human behavior in close-interaction scenarios is crucial for enabling realistic virtual interactions in augmented reality, pre
arXiv:2604.13847v1 Announce Type: new Abstract: While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogene
arXiv:2604.13192v1 Announce Type: cross Abstract: Robust control barrier functions (CBFs) provide a principled mechanism for smooth safety enforcement under worst-case disturbances. However, existing
arXiv:2604.13538v1 Announce Type: new Abstract: Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the exis
arXiv:2604.13789v1 Announce Type: new Abstract: 3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first fram
arXiv:2510.26519v3 Announce Type: replace Abstract: Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable
arXiv:2604.14084v1 Announce Type: new Abstract: On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter
arXiv:2604.13368v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among P
Today we’re announcing Ternary Bonsai: Top intelligence at 1.58 bits Using ternary weights {-1, 0, +1}, we built a family of models that are 9x smaller than their 16-bit counterparts while outperformi
arXiv:2604.13519v1 Announce Type: new Abstract: Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM
arXiv:2603.15620v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models excel in static manipulation but struggle in dynamic environments with moving targets. This performance gap prim
arXiv:2604.13322v1 Announce Type: new Abstract: Raveling, the loss of aggregates, is a major form of asphalt pavement surface distress, especially on highways. While research has shown that machine le
arXiv:2604.05478v2 Announce Type: replace-cross Abstract: Immune checkpoint inhibitors (ICIs) have transformed cancer therapy; yet substantial proportion of patients exhibit intrinsic or acquired resi
arXiv:2604.14116v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks, automating complex, real-world workflows, s
arXiv:2601.10245v2 Announce Type: replace-cross Abstract: Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to comp
arXiv:2604.13565v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such
arXiv:2604.13383v1 Announce Type: new Abstract: Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IF
arXiv:2604.13596v1 Announce Type: new Abstract: Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for app
arXiv:2604.13654v1 Announce Type: new Abstract: Vision-and-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) represents a pivotal challenge in embodied artificial intelligence, focused on ena
arXiv:2603.08486v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods req
VLM Performance：Qwen3.6 is natively multimodal, and Qwen3.6-35B-A3B showcases perception and multimodal reasoning capabilities that far exceed what its size would suggest, with only around 3 billion a
arXiv:2604.13438v1 Announce Type: new Abstract: Privacy concerns in LLMs have led to the rapidly growing need to enforce a data's 'right to be forgotten'. Machine unlearning addresses precisely this t
arXiv:2603.26259v2 Announce Type: replace-cross Abstract: While Late Interaction models exhibit strong retrieval performance, many of their underlying dynamics remain understudied, potentially hiding
arXiv:2603.27557v2 Announce Type: replace-cross Abstract: In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generalit
arXiv:2604.11983v1 Announce Type: cross Abstract: In this paper, we propose the geometric algebra-informed neural radiance fields (GAI-NeRF), a novel framework for wireless channel prediction that lev
arXiv:2505.14264v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models (LLMs), esp
arXiv:2501.16154v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models sho
arXiv:2604.12945v1 Announce Type: cross Abstract: Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equall
arXiv:2505.17086v4 Announce Type: replace Abstract: Large Language Models (LLMs) equipped with modern Retrieval-Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to inte
New research from MIT and Stanford examines how AI systems can detect and exploit users' pre-existing cognitive biases — such as confirmation bias and political leanings — to tailor responses in ways
arXiv:2603.21011v2 Announce Type: replace-cross Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational enginee
arXiv:2510.01186v2 Announce Type: replace Abstract: While existing video editing methods excel with single subjects, they struggle in dense, multi-subject scenes, frequently suffering from attention d
Banger paper from NVIDIA. Agentic reasoning needs models that are not just capable, but efficient at long-context inference. The agent model layer is moving toward open, long-context, high-throughput
arXiv:2604.12221v1 Announce Type: new Abstract: Gait recognition, as a reliable biometric technology, has seen rapid development in recent years while it faces significant challenges caused by diverse
arXiv:2604.12138v1 Announce Type: new Abstract: RAG systems have transformed how LLMs access external knowledge, but we find that current implementations exhibit a bias toward factual, objective conte
arXiv:2604.12196v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate multiple candidate responses for a given prompt, yet selecting the most reliable one remains challengin
arXiv:2604.12119v1 Announce Type: new Abstract: Large vision-language models (VLMs) often rely on familiar semantic priors, but existing evaluations do not cleanly separate perception failures from ru
arXiv:2604.12325v1 Announce Type: cross Abstract: We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past expe
arXiv:2604.12966v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-gr
arXiv:2508.18187v2 Announce Type: replace-cross Abstract: Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become w
arXiv:2604.12341v1 Announce Type: new Abstract: As generative image editing advances, image manipulation localization (IML) must handle both traditional manipulations with conspicuous forensic artifac
arXiv:2604.12632v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity th
arXiv:2602.00181v3 Announce Type: replace-cross Abstract: Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat t
arXiv:2604.12262v1 Announce Type: cross Abstract: Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, singl
arXiv:2507.21990v4 Announce Type: replace-cross Abstract: Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoni
arXiv:2604.12767v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing