Knowledge catalogue
arXiv:2602.01297v3 Announce Type: replace Abstract: Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges fo
arXiv:2604.26506v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial prompts -- adversarial instruc
arXiv:2601.04389v2 Announce Type: replace-cross Abstract: Current safety evaluations of large language models (LLMs) create a dangerous illusion of universal protection by aggregating harms under gene
arXiv:2604.26355v1 Announce Type: new Abstract: Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains unde
arXiv:2602.03412v2 Announce Type: replace Abstract: As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamenta
arXiv:2604.25098v1 Announce Type: cross Abstract: While current Large Language Models (LLMs) exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), their massive parameter
arXiv:2602.11786v2 Announce Type: replace Abstract: Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety through breadth-oriented evaluation acr
arXiv:2604.24827v1 Announce Type: new Abstract: Closed-source frontier labs do not disclose parameter counts, and the standard alternative -- inference economics -- carries 2imes+ uncertainty from har
arXiv:2604.24971v1 Announce Type: cross Abstract: We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocat
arXiv:2604.03472v2 Announce Type: replace Abstract: Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without huma
arXiv:2604.22840v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong potential in agentic tasks, particularly in slide generation. However, slide generation poses a
arXiv:2512.20164v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content mo
arXiv:2404.10141v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) models have achieved remarkable progress in high-quality image synthesis, yet most benchmarks rely on simple, self-contain
arXiv:2603.27507v2 Announce Type: replace Abstract: Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods s
arXiv:2604.22820v1 Announce Type: cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks for recovery and exploration, but added multi-agent workflow flexibil
arXiv:2604.23987v1 Announce Type: new Abstract: Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspect
This post discusses how large language models (LLMs) could serve as future chief financial officers, with Mercury as a platform enabling AI systems to manage finances and financial operations. The con
arXiv:2604.23478v1 Announce Type: new Abstract: Large language models are increasingly deployed as automated judges for evaluating other models, yet the stability of their verdicts under semantically
arXiv:2506.11480v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data ineffic
arXiv:2604.23855v1 Announce Type: new Abstract: We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The a
arXiv:2601.21321v2 Announce Type: replace Abstract: This paper proposes White-Op, an operational amplifier (op-amp) behavioral-level parameter design framework assisted by the human-mimicking reasonin
arXiv:2604.24715v1 Announce Type: new Abstract: Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transforme
arXiv:2509.25414v2 Announce Type: replace-cross Abstract: Large language models are often adapted using parameter-efficient techniques such as Low-Rank Adaptation (LoRA), formulated as y = W_0x + BAx,
arXiv:2505.02922v3 Announce Type: replace Abstract: Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and band
arXiv:2604.23577v1 Announce Type: new Abstract: Serving diverse NLP workloads with large language models is costly: at one enterprise partner, inference costs exceeded $200K/month despite over 70% of
arXiv:2511.01490v2 Announce Type: replace Abstract: As synthetic data becomes widely used in language model development, understanding its impact on model behavior is crucial. This paper investigates
arXiv:2604.24088v1 Announce Type: cross Abstract: Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of inte
arXiv:2604.23398v1 Announce Type: new Abstract: We report a reproducible error pattern in GPT-5.4 on OWL~2~DL compliance queries: the model frequently answers ``unknown'' when the reasoner-entailed an
arXiv:2604.22606v1 Announce Type: new Abstract: Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sound
arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining creates a subtle but
arXiv:2604.22438v1 Announce Type: cross Abstract: Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing appr
arXiv:2505.20435v3 Announce Type: replace-cross Abstract: Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlook
arXiv:2604.20913v1 Announce Type: new Abstract: Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. We
arXiv:2603.07101v3 Announce Type: replace Abstract: Creatively translating complex gameplay ideas into executable artifacts (e.g., games as Unity projects and code) remains a central challenge in comp
arXiv:2604.21026v1 Announce Type: new Abstract: Deploying large language models to heterogeneous hardware is often constrained by memory, not compute. We introduce MCAP (Monte Carlo Activation Profili
arXiv:2604.21098v1 Announce Type: new Abstract: Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned b
arXiv:2604.21571v1 Announce Type: new Abstract: Current model training approaches incorporate user information directly into shared weights, making individual data removal computationally infeasible w
arXiv:2604.19974v1 Announce Type: cross Abstract: Large language models can be uncertain yet correct, or confident yet wrong, raising the question of whether their output-level uncertainty and their a
arXiv:2601.03396v2 Announce Type: replace Abstract: Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underex
arXiv:2604.19884v1 Announce Type: cross Abstract: Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded
arXiv:2604.19783v1 Announce Type: new Abstract: Which persuasion strategies, if any, are associated with donation compliance? Answering this requires fine-grained strategy labels across a full corpus
arXiv:2502.12911v3 Announce Type: replace Abstract: Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL ge
arXiv:2604.20685v1 Announce Type: new Abstract: Aligning large language models (LLMs) to desirable human values requires balancing multiple, potentially conflicting objectives such as helpfulness, tru
arXiv:2412.14590v2 Announce Type: replace Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions sti
arXiv:2602.07085v2 Announce Type: replace-cross Abstract: Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime
arXiv:2603.29025v2 Announce Type: replace-cross Abstract: Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon
arXiv:2604.19716v1 Announce Type: new Abstract: Large Language Models (LLMs) still struggle with multi-step logical reasoning. Existing approaches either purely refine the reasoning chain in natural l
arXiv:2604.18901v1 Announce Type: cross Abstract: Harmful intent is geometrically recoverable from large language model residual streams: as a linear direction in most layers, and as angular deviation
arXiv:2604.18897v1 Announce Type: new Abstract: We present a systematic empirical study of prompt engineering for formal mathematical reasoning in the context of the SAIR Equational Theories Stage 1 c
arXiv:2604.18803v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly deployed in settings where reliable visual grounding carries operational consequences, yet their behavi
arXiv:2604.19162v1 Announce Type: new Abstract: This paper studies uncertainty quantification for large language models (LLMs) under black-box access, where only a small number of responses can be sam
arXiv:2512.09427v5 Announce Type: replace-cross Abstract: Existing memory management techniques severely hinder efficient Large Language Model serving on accelerators constrained by poor random-access
arXiv:2604.19060v1 Announce Type: new Abstract: Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improv
arXiv:2602.11675v3 Announce Type: replace Abstract: Large language models may answer causal questions correctly for the wrong reasons, substituting associational shortcuts P(Y|X) for the interventiona
arXiv:2604.18592v1 Announce Type: cross Abstract: We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large langua
arXiv:2604.18655v1 Announce Type: cross Abstract: Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and ru
This guide from Databricks covers practical techniques and best practices for fine-tuning large language models, including methodologies for adapting pre-trained LLMs to specific tasks and domains. It
arXiv:2604.17889v1 Announce Type: new Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such sc
arXiv:2604.17255v1 Announce Type: new Abstract: Accurate comprehension and controllable generation of emotion and rhetoric are pivotal for enhancing the reasoning capabilities of large language models