Knowledge catalogue
arXiv:2604.11802v1 Announce Type: new Abstract: Using psychological constructs such as the Big Five, large language models (LLMs) can imitate specific personality profiles and predict a user's persona
arXiv:2505.04842v2 Announce Type: replace-cross Abstract: Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value func
arXiv:2602.19509v3 Announce Type: replace-cross Abstract: We observe that LLM cascading and routing implicitly solves an anytime computation problem -- a class of algorithms, well-studied in classical
arXiv:2604.10687v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance in text summarization, yet their effectiveness drops significantly across languages with res
arXiv:2604.10933v1 Announce Type: cross Abstract: Deep neural networks remain highly vulnerable to adversarial perturbations, limiting their reliability in security- and safety-critical applications.
arXiv:2511.04776v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (GenAI) represents a rapidly expanding digital infrastructure whose energy demand and associated CO2 emissi
arXiv:2511.03636v2 Announce Type: replace-cross Abstract: We perform a simulation-based forecasting analysis to compare the cosmological constraining power of higher-order summary statistics of the la
arXiv:2603.18893v2 Announce Type: replace Abstract: Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current
arXiv:2604.11501v1 Announce Type: cross Abstract: We compare two strategies for compressing the KV cache in transformer inference: rank reduction (discard dimensions) and quantization (keep all dimens
arXiv:2508.19600v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, th
arXiv:2604.11112v1 Announce Type: cross Abstract: Class-incremental learning (CIL) aims to continuously accumulate knowledge from a stream of tasks and construct a unified classifier over all seen cla
arXiv:2604.10857v1 Announce Type: cross Abstract: Diffusion models generate samples by iteratively querying learned score estimates. A rapidly growing literature focuses on accelerating sampling by mi
arXiv:2503.23001v5 Announce Type: replace Abstract: The deployment of large language models (LLMs) for next-generation network optimization introduces novel data governance challenges. mobile network
arXiv:2604.09681v1 Announce Type: cross Abstract: With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time in
arXiv:2604.11164v1 Announce Type: new Abstract: Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotat
arXiv:2604.10188v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG). However, existing methods implicitly assume high-
arXiv:2604.10960v1 Announce Type: new Abstract: Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT
arXiv:2604.11626v1 Announce Type: new Abstract: Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference.
arXiv:2604.10740v1 Announce Type: new Abstract: Despite the widespread adoption of Large Language Models (LLMs) in Legal AI, their utility for automated contract revision remains impeded by hallucinat
arXiv:2604.10568v1 Announce Type: new Abstract: Systematic chemical names, such as IUPAC-style nomenclature for metal-organic frameworks (MOFs), contain rich structural and compositional information i
arXiv:2604.10259v1 Announce Type: new Abstract: We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi
arXiv:2604.09675v1 Announce Type: cross Abstract: Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted agent interactions and dropped c
arXiv:2604.10213v1 Announce Type: cross Abstract: Reliable LiDAR perception requires robustness across sensors, environments, and adverse weather. However, existing datasets rarely provide physically
arXiv:2506.16796v4 Announce Type: replace Abstract: Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate unde
arXiv:2604.10072v1 Announce Type: new Abstract: Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Tho
arXiv:2604.10908v1 Announce Type: new Abstract: Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(A
arXiv:2603.01692v3 Announce Type: replace-cross Abstract: LLM-based agents for machine learning engineering (MLE) predominantly rely on tree search, a form of gradient-free optimization that uses scal
arXiv:2604.11399v1 Announce Type: cross Abstract: Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from languag
arXiv:2604.09963v1 Announce Type: cross Abstract: Microreboot enables fast recovery by restarting only the failing component, but in modern microservices naive restarts are unsafe: dense dependencies
arXiv:2604.11229v1 Announce Type: cross Abstract: Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, conte
arXiv:2603.16630v2 Announce Type: replace Abstract: High-performance closed-loop control of truly soft continuum manipulators has remained elusive. Experimental demonstrations have largely relied on s
arXiv:2604.10442v1 Announce Type: new Abstract: Effective poster design requires rapidly capturing attention and clearly conveying messages. Inspired by the ``contrast effects'' principle, we propose
arXiv:2604.11109v1 Announce Type: cross Abstract: As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware ge
arXiv:2509.22055v2 Announce Type: replace Abstract: We introduce RedNote-Vibe, a dataset spanning five years (pre-LLM to July 2025) sourced from lifestyle platform RedNote (Xiaohongshu), capturing the
arXiv:2604.11141v1 Announce Type: new Abstract: Although LLMs drive automation, it is critical to ensure immense consideration for high-stakes enterprise workflows such as those involving legal matter
arXiv:2604.10520v1 Announce Type: cross Abstract: As Large Language Models (LLMs) have become capable of generating long and descriptive code summaries, accurate and reliable evaluation of factual con
arXiv:2604.11223v1 Announce Type: cross Abstract: We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value x_i to
arXiv:2604.09916v1 Announce Type: new Abstract: Simultaneous Speech Translation (SimulST) requires balancing high translation quality with low latency. Recent work introduced REINA, a method that trai
arXiv:2604.10578v1 Announce Type: new Abstract: The growing demand for Embodied AI and VR applications has highlighted the need for synthesizing high-quality 3D indoor scenes from sparse inputs. Howev
arXiv:2603.09172v4 Announce Type: replace-cross Abstract: We present improved lower bounds for seven classical Ramsey numbers: mathbf{R}(3, 13) is increased from 60 to 61, mathbf{R}(3, 18) from 99 to
arXiv:2406.05358v3 Announce Type: replace Abstract: Intensity control is a class of continuous-time dynamic optimization problems with many important applications in Operations Research including queu
arXiv:2604.09870v1 Announce Type: cross Abstract: We investigate how looped transformers encode human preference in their internal iteration states. Using Ouro-2.6B-Thinking, a 2.6B-parameter looped t
arXiv:2604.10212v1 Announce Type: new Abstract: Language models can be used to identify relationships between financial entities in text. However, while structured output mechanisms exist, prompting-b
arXiv:2507.11019v4 Announce Type: replace Abstract: Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their h
arXiv:2604.11554v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language mode
arXiv:2508.04436v2 Announce Type: replace Abstract: Autonomous highway driving involves high-speed safety risks due to limited reaction time, where rare but dangerous events may lead to severe consequ
arXiv:2508.03306v4 Announce Type: replace-cross Abstract: Lowering the numerical precision of model parameters and computations is widely adopted to improve the efficiency of retrieval systems. Howeve
arXiv:2604.10423v1 Announce Type: new Abstract: Replicability requires that algorithmic conclusions remain consistent when rerun on independently drawn data. A central structural question is compositi
arXiv:2604.10789v1 Announce Type: new Abstract: Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D sc
arXiv:2604.11278v1 Announce Type: new Abstract: In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use
arXiv:2604.11707v1 Announce Type: new Abstract: Accurate future video prediction requires both high visual fidelity and consistent scene semantics, particularly in complex dynamic environments such as
arXiv:2604.09982v1 Announce Type: cross Abstract: Reproducibility must validate architectural robustness, not just numerical accuracy. We evaluate ColBERT-v2 and ConstBERT across five dimensions, find
arXiv:2604.10842v1 Announce Type: cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol~(MCP) to read and write files on a developer's wo
arXiv:2603.24853v2 Announce Type: replace Abstract: Ethical debates in AI have primarily focused on back-end issues such as data governance, model training, and algorithmic decision-making. Less atten
arXiv:2603.16068v3 Announce Type: replace-cross Abstract: Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LL
arXiv:2604.11082v1 Announce Type: new Abstract: Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot scale to the growing test surface of
arXiv:2604.11080v1 Announce Type: cross Abstract: Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large La
arXiv:2603.14968v2 Announce Type: replace-cross Abstract: While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, req
arXiv:2604.10465v1 Announce Type: cross Abstract: Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically
arXiv:2604.11056v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved the reasoning ability of Large Language Models (LLMs). However, its s