Knowledge catalogue
arXiv:2606.04703v1 Announce Type: new Abstract: Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward c
arXiv:2602.06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications,
arXiv:2606.04057v1 Announce Type: cross Abstract: Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cu
arXiv:2602.04613v2 Announce Type: replace Abstract: Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) h
arXiv:2606.03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and r
arXiv:2606.03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little
arXiv:2606.03070v1 Announce Type: cross Abstract: Asynchronous reinforcement learning can improve language-model post-training throughput by decoupling response generation from policy optimization, bu
arXiv:2606.03328v1 Announce Type: cross Abstract: Post-training pruning compresses large language models to high sparsity using a small unlabelled calibration set, and recent work has concluded that t
arXiv:2606.03657v1 Announce Type: new Abstract: Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a functi
arXiv:2512.03019v2 Announce Type: replace-cross Abstract: Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation
arXiv:2606.02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely co
arXiv:2606.03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively
arXiv:2606.03876v1 Announce Type: cross Abstract: With the growing prevalence of modern ubiquitous computing technologies, multi-modal tracking systems hold promise for providing timely awareness and
arXiv:2606.02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset thr
arXiv:2606.03641v1 Announce Type: new Abstract: We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient'
arXiv:2510.21011v3 Announce Type: replace-cross Abstract: As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational b
arXiv:2510.17149v3 Announce Type: replace Abstract: As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and
arXiv:2606.03136v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails: they operate on individual turns, while attacks
arXiv:2606.03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resource constraints. Tensor decompositions have emerged
arXiv:2510.00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise re
arXiv:2606.00198v1 Announce Type: cross Abstract: While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should t
arXiv:2509.06948v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the
arXiv:2606.02372v1 Announce Type: new Abstract: Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, ex
arXiv:2606.01441v1 Announce Type: new Abstract: Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve in
arXiv:2603.08026v2 Announce Type: replace-cross Abstract: Masked diffusion language models enable parallel token decoding, providing a promising alternative to the sequential nature of autoregressive
arXiv:2606.01828v1 Announce Type: cross Abstract: Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specializati
arXiv:2606.02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted
Generate a complete storyboard from a single prompt, then animate it in Seedance 2.0 using a reference image. This ComfyUI workflow uses LLMs to expand prompts, create storyboard scenes, and format ev
arXiv:2606.00860v1 Announce Type: cross Abstract: Self-report questionnaires remain the prevailing tool for probing the psychological states of persona-conditioned agents (PC-Agents). However, classic
arXiv:2606.00750v1 Announce Type: new Abstract: Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing
arXiv:2606.01204v1 Announce Type: cross Abstract: We investigate whether large language models produce different medical triage recommendations for identical symptoms based solely on the language of t
arXiv:2606.01711v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks, yet the quadratic computation
arXiv:2512.10234v2 Announce Type: replace-cross Abstract: Even LLMs that appear safe during evaluation can still produce harmful responses in deployment. Because stochastic sampling yields different r
arXiv:2606.00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely attributed to the advent of Large Language Models
arXiv:2606.00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider. Multilingual deployment m
arXiv:2606.02470v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has emerged as a transformative standard for connecting large language models (LLMs) with external data sources and too
arXiv:2606.00888v1 Announce Type: cross Abstract: Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference efficiency of deep neural networks; however, we fin
arXiv:2606.02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a
arXiv:2511.05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practica
arXiv:2606.00395v1 Announce Type: cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs ofte
arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration to
arXiv:2602.12984v2 Announce Type: replace Abstract: Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely ov
arXiv:2606.01912v1 Announce Type: new Abstract: Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferen
arXiv:2606.02184v1 Announce Type: cross Abstract: These names do not exist. Elena Vasquez and Marcus Chen have appeared as volcano experts, astronauts, thriller protagonists, podcast hosts, and academ
arXiv:2606.01755v1 Announce Type: new Abstract: Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsiste
arXiv:2606.01252v1 Announce Type: cross Abstract: Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as
If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painf
arXiv:2605.30804v1 Announce Type: new Abstract: We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and Japanese. Three were developed primarily for Engl
arXiv:2603.09221v2 Announce Type: replace Abstract: Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal
arXiv:2605.31494v1 Announce Type: new Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by
arXiv:2605.11946v2 Announce Type: replace Abstract: Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchm
arXiv:2605.31164v1 Announce Type: cross Abstract: Training data plays a central role in large language models (LLMs) optimization, motivating extensive research on data scheduling strategies. Most exi
arXiv:2605.30859v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail r
arXiv:2605.30861v1 Announce Type: new Abstract: Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRP
arXiv:2605.31381v1 Announce Type: new Abstract: We evaluate the consistency of automated judges in conducting a multi-dimensional safety evaluation in a reference-free setup. Our results indicate that
arXiv:2602.13069v2 Announce Type: replace-cross Abstract: On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints
arXiv:2510.07651v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all
arXiv:2510.01137v3 Announce Type: replace Abstract: Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and differentially private stochastic gradient descent
arXiv:2605.31113v1 Announce Type: new Abstract: Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such a
arXiv:2605.29396v1 Announce Type: new Abstract: Safety alignment for large language models (LLMs) aims to reduce harmful or unsafe behavior while preserving general utility. However, recent findings r