Knowledge catalogue
arXiv:2605.25648v1 Announce Type: cross Abstract: This paper proposes StrTransformer, a source-wise structured Transformer framework for blind source recovery and branch-wise latent modeling. Instead
arXiv:2603.17198v2 Announce Type: replace-cross Abstract: A foundational principle in cognitive science holds that intelligent agents do not learn by storing experiences as isolated instances, but by
arXiv:2605.24564v1 Announce Type: new Abstract: Backtesting large language models (LLMs) on historical financial data is unreliable because pre-training cuts off after the events happened. An LLM trai
arXiv:2605.25928v1 Announce Type: new Abstract: We describe the winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. The task requires produ
arXiv:2605.24556v1 Announce Type: cross Abstract: Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilin
arXiv:2605.24846v1 Announce Type: cross Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently un
arXiv:2605.24873v1 Announce Type: cross Abstract: Despite the importance of causal reasoning, training LLMs to reason causally remains underexplored. Existing data efforts mostly focus on benchmarking
arXiv:2605.25969v1 Announce Type: new Abstract: Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and
arXiv:2605.25836v1 Announce Type: cross Abstract: Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not mi
arXiv:2605.25820v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns e
arXiv:2605.24524v1 Announce Type: cross Abstract: In non-invasive neural language decoding, results can be inflated by sources that are not stimulus-evoked neural evidence: decoder priors, embedding-b
arXiv:2605.23932v1 Announce Type: new Abstract: Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis unde
arXiv:2605.26046v1 Announce Type: cross Abstract: Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual
arXiv:2509.10452v2 Announce Type: replace Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In man
arXiv:2605.23972v1 Announce Type: new Abstract: Large language models achieve strong performance in language generation and knowledge-intensive tasks, yet remain limited in settings requiring causal r
arXiv:2605.05997v2 Announce Type: replace Abstract: Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vis
arXiv:2605.23247v1 Announce Type: new Abstract: In this paper, we introduce the first machine learning framework for predicting optimal processing times in Single-Level Tree Network (SLTN) architectur
arXiv:2605.23809v1 Announce Type: cross Abstract: The Open Radio Access Network (O-RAN) architecture allows AI to be embedded directly into the RAN through modular xApps and rApps, yet creating these
arXiv:2605.23448v1 Announce Type: cross Abstract: This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than o
arXiv:2602.05472v2 Announce Type: replace Abstract: The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent extit{reward bottleneck}: traditional reinfor
arXiv:2603.17879v2 Announce Type: replace-cross Abstract: This work presents a multi-label temporal event detection framework for video capsule endoscopy (VCE) that addresses the extreme class imbalan
arXiv:2605.23147v1 Announce Type: cross Abstract: Role prompts of the form As X, do Y admit a clean linear decomposition at one specific site in the residual stream: the prompt-to-answer transition --
arXiv:2605.23497v1 Announce Type: new Abstract: Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds
arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe co
arXiv:2602.11146v2 Announce Type: replace-cross Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computatio
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2605.23590v1 Announce Type: new Abstract: ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which r
arXiv:2605.23116v1 Announce Type: cross Abstract: Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs.
arXiv:2605.23491v1 Announce Type: cross Abstract: Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verif
arXiv:2511.15503v2 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Le
arXiv:2601.16027v2 Announce Type: replace Abstract: The rise of live streaming has transformed online interaction, enabling massive real-time engagement but also exposing platforms to complex risks su
arXiv:2605.23281v1 Announce Type: new Abstract: Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across div
arXiv:2605.23605v1 Announce Type: cross Abstract: Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality
arXiv:2605.23635v1 Announce Type: cross Abstract: Traditional neural networks provide deterministic predictions without inherent uncertainty estimates. While Bayesian Neural Networks (BNNs) offer a pr
arXiv:2605.23493v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without intr
arXiv:2509.26383v5 Announce Type: replace-cross Abstract: Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs
arXiv:2605.23451v1 Announce Type: new Abstract: Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Rea
arXiv:2605.23163v1 Announce Type: new Abstract: End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficie
arXiv:2605.22954v1 Announce Type: new Abstract: Multi-center survival prediction can improve robustness and generalizability, yet privacy regulations and institutional governance often prevent pooling
arXiv:2605.22848v1 Announce Type: cross Abstract: Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive f
arXiv:2605.22882v1 Announce Type: new Abstract: Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As
arXiv:2605.23078v1 Announce Type: cross Abstract: Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters.
arXiv:2605.22885v1 Announce Type: new Abstract: Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data
arXiv:2605.22967v1 Announce Type: new Abstract: When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, f
arXiv:2605.23510v1 Announce Type: new Abstract: When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-in
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approac
arXiv:2605.22976v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and abilit
arXiv:2605.23507v1 Announce Type: new Abstract: The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low re
arXiv:2605.23840v1 Announce Type: new Abstract: Mueller matrix imaging provides rich, physically meaningful contrast for biomedical tissue analysis, but supervised learning is hindered by scarce dense
arXiv:2605.23885v1 Announce Type: new Abstract: Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. Wh
arXiv:2602.20210v2 Announce Type: replace-cross Abstract: Crystal modeling spans a family of conditional and unconditional generation tasks, including crystal structure prediction (CSP) and de novo ge
arXiv:2605.22850v1 Announce Type: cross Abstract: Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests t
arXiv:2605.23019v1 Announce Type: new Abstract: Deploying language-model agents in production often requires substantial compute and human effort to tune prompts, parsers, validators, and other compon
arXiv:2605.23296v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based su
arXiv:2605.23074v1 Announce Type: new Abstract: The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating l
arXiv:2605.23559v1 Announce Type: cross Abstract: Whole-slide image visual question answering (WSI-VQA) frames pathology as an extreme-context search problem: to answer a free-form clinical query, a s
arXiv:2506.20537v3 Announce Type: replace Abstract: Efficient simulation of Laser Powder Bed Fusion (LPBF) is crucial for process prediction due to the lasting issue of high computational cost associa
arXiv:2605.23128v1 Announce Type: new Abstract: Currently, Vision-Language-Action (VLA) models have become the most adopted paradigm for robotic manipulation for its great potential for task generaliz
arXiv:2605.23902v1 Announce Type: new Abstract: Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space
arXiv:2605.23603v1 Announce Type: cross Abstract: We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from m