Knowledge catalogue
arXiv:2602.23297v2 Announce Type: replace Abstract: Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as
arXiv:2504.08791v3 Announce Type: replace-cross Abstract: On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low thr
arXiv:2607.04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-
arXiv:2602.13517v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). Howev
arXiv:2607.02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.
arXiv:2607.04969v1 Announce Type: cross Abstract: The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited
arXiv:2607.04728v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of 'rollout then update', which inevitably res
arXiv:2607.04945v1 Announce Type: new Abstract: LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically
arXiv:2607.01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural
arXiv:2607.01457v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distin
arXiv:2607.01237v1 Announce Type: cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high d
arXiv:2607.02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal met
arXiv:2607.01830v1 Announce Type: new Abstract: Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a
arXiv:2607.02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in s
arXiv:2607.02504v1 Announce Type: cross Abstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on extbf{sp
arXiv:2607.01951v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat
arXiv:2607.01293v1 Announce Type: new Abstract: We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named En
arXiv:2607.00292v1 Announce Type: cross Abstract: Designing deployable and resilient network topologies from natural language requirements remains a challenging problem in network automation. This wor
arXiv:2607.00501v1 Announce Type: cross Abstract: We present BaseRT, a native Metal inference runtime for large language models (LLMs) on Apple Silicon, and report the highest inference throughput on
arXiv:2607.00908v1 Announce Type: new Abstract: Mixed-precision quantization (MPQ) has become a key technique for deploying large language models under stringent memory and compute constraints. We fir
arXiv:2607.00368v1 Announce Type: new Abstract: Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, ta
arXiv:2511.06160v2 Announce Type: replace Abstract: While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of social bias emerge during complex logical reasoning tas
arXiv:2607.00003v1 Announce Type: cross Abstract: Personal Knowledge Graphs (PKGs) offer a privacy-preserving framework for modeling user preferences, yet constructing them from unstructured, decentra
arXiv:2407.10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to
arXiv:2607.00848v1 Announce Type: new Abstract: In this opinion paper, we propose MetaHOPE, an error severity-aware annotation framework for evaluating metaphor translations. Metaphors present challen
arXiv:2509.21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before
arXiv:2607.00158v1 Announce Type: new Abstract: Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether
arXiv:2607.00008v1 Announce Type: cross Abstract: Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In
arXiv:2607.00274v1 Announce Type: cross Abstract: Effective writing feedback is among the strongest drivers of student learning, yet producing it at scale is labor-intensive. LLMs offer a natural path
arXiv:2503.13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful,
arXiv:2606.31903v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acce
arXiv:2606.30850v1 Announce Type: new Abstract: Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic unce
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these co
arXiv:2606.30963v1 Announce Type: cross Abstract: Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeti
arXiv:2606.31519v1 Announce Type: cross Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often
arXiv:2606.31307v1 Announce Type: new Abstract: Large language models used in task-oriented dialogue often produce fluent but unsafe responses when backend database calls fail, return empty results, o
This post describes a common architectural pattern for integrating memory components into AI systems, illustrated through examples like DeepWiki and AutoWiki that automatically generate and maintain k
arXiv:2606.17041v4 Announce Type: replace Abstract: Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregati
arXiv:2606.29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and whe
arXiv:2606.30420v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for improving the reasoning capabilities of large language models (LLMs). H
arXiv:2606.28749v1 Announce Type: cross Abstract: Although most undergraduates now use large language models (LLMs), a form of generative artificial intelligence (GenAI) for academic writing, no valid
arXiv:2510.01878v2 Announce Type: replace Abstract: Low-rank gradient optimization for large language models is currently divided into two categories: structured methods that rigorously identify subsp
arXiv:2606.28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, model
arXiv:2606.30005v1 Announce Type: new Abstract: Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management age
arXiv:2602.13562v2 Announce Type: replace-cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measu
arXiv:2606.30406v1 Announce Type: new Abstract: Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabili
arXiv:2606.29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires con
arXiv:2606.29158v1 Announce Type: cross Abstract: Learning-rate transfer can reduce the cost of training large language models: instead of sweeping learning rates at target scale, practitioners extrap
arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-
arXiv:2606.28796v1 Announce Type: new Abstract: Government documents in India are predominantly issued in regional languages such as Marathi, creating substantial accessibility barriers for non-native
arXiv:2606.28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defen
arXiv:2606.27457v1 Announce Type: cross Abstract: Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single m
arXiv:2606.27550v1 Announce Type: new Abstract: Multi-token prediction has been shown to increase data density during training, improve downstream text-generation quality, and serves as the defacto ap
arXiv:2606.17524v2 Announce Type: replace Abstract: Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where
arXiv:2606.27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We invest
arXiv:2606.28116v1 Announce Type: new Abstract: Frontier large language model training consumes massive accelerator fleets and long wall-clock computation, making stability failures costly when they o
arXiv:2606.27785v1 Announce Type: cross Abstract: Training-free compression methods for large language models (LLMs) often use calibration data to guide compression decisions. ROCKET, a recent method
arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments
arXiv:2606.27443v1 Announce Type: new Abstract: Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-exp
arXiv:2606.26698v1 Announce Type: cross Abstract: In today's fast-paced information era, logical fallacies, defined as defective patterns of reasoning, inevitably contribute to the growth of informati