Knowledge catalogue
arXiv:2606.26861v1 Announce Type: new Abstract: Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning
arXiv:2606.26120v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirect
arXiv:2606.26629v1 Announce Type: cross Abstract: Weight-space regularization methods such as Elastic Weight Consolidation (EWC) are the standard approach to catastrophic forgetting in continual learn
arXiv:2606.27210v1 Announce Type: new Abstract: We argue that safety classifiers should model user intent as an explicit signal between the prompt and the final label. To study this, we introduce AIMS
arXiv:2606.26403v1 Announce Type: new Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and longi
arXiv:2509.01412v3 Announce Type: replace Abstract: Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugg
arXiv:2606.26348v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their c
arXiv:2606.26935v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning is widely used in language-model agents, but prior work has shown that verbalized CoT is not always faithful and may in
arXiv:2606.25608v1 Announce Type: cross Abstract: This paper presents a novel approach to perform semi-automated BSI IT-Grundschutz certification using a MultiLarge Language Model system (MLS) with Hy
arXiv:2606.25524v1 Announce Type: cross Abstract: Large language models (LLMs) reach high accuracy in mathematical reasoning, but individual traces on the same problem diverge; some arrive at the corr
arXiv:2606.25332v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptibl
arXiv:2606.24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of t
arXiv:2606.25941v1 Announce Type: cross Abstract: Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, includin
arXiv:2606.25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and
arXiv:2606.24973v1 Announce Type: new Abstract: We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken at age ~16), spanning
arXiv:2512.10187v3 Announce Type: replace Abstract: LLMs excel at reasoning, but validating their steps remains challenging. Formal verification offers a solution through mechanically checkable proofs
arXiv:2606.26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-h
arXiv:2606.24890v1 Announce Type: new Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia? We show that they can. Wikipedia appears in near
arXiv:2606.24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting f
arXiv:2606.24459v1 Announce Type: cross Abstract: Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition variations, and limited labeled data occur simultane
arXiv:2606.24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferr
arXiv:2606.22475v1 Announce Type: cross Abstract: Modern web applications increasingly combine three ingredients that are hard to test: output from large language models, multi-market internationaliza
arXiv:2606.21083v1 Announce Type: cross Abstract: Large language models (LLMs) deployed for logical reasoning in knowledge-intensive domains exhibit a subtle but critical failure: coherence can be vac
arXiv:2602.22642v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has substantially empowered Large Language Models (LLMs) to tackle complex reasoning tasks, yet the verbose nature of explici
arXiv:2606.21023v1 Announce Type: new Abstract: As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict syst
arXiv:2606.22932v1 Announce Type: new Abstract: Reverse-mode differentiation computes every weight gradient, writes it to memory, and only then lets the optimizer read it back. This two-phase schedule
arXiv:2606.21633v1 Announce Type: new Abstract: Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still gro
arXiv:2606.17702v2 Announce Type: replace Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extracti
arXiv:2606.21090v1 Announce Type: cross Abstract: Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within t
arXiv:2606.22873v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the
arXiv:2606.21008v1 Announce Type: cross Abstract: The metanym game is a competitive word game for LLMs that measures structural intelligence against established cognitive-science constructs. No conten
arXiv:2602.07078v2 Announce Type: replace Abstract: Reinforcement Learning (RL) for Large Language Models (LLMs) often suffers from training collapse in long-horizon tasks due to exploding gradient va
arXiv:2606.21847v1 Announce Type: new Abstract: Low-rank decomposition serves as a promising compression paradigm for large language models, however, rank allocation remains challenging: manual rules
arXiv:2506.08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely
arXiv:2603.24080v2 Announce Type: replace Abstract: Benchmarks like MMLU suggest flagship language models approach factuality saturation above 90%. LLMpedia shows this picture is incomplete. We materi
arXiv:2606.11316v1 Announce Type: new Abstract: Large language models are increasingly deployed across professional domains, bringing hard-to-predict risks, including the generation of harmful or disr
arXiv:2601.04710v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) achieves strong performance but is often limited by the memory overhead of backpropagation. Zeroth-order (Z
arXiv:2511.21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to
arXiv:2606.11599v1 Announce Type: new Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depen
arXiv:2606.11375v1 Announce Type: cross Abstract: Standard linear probing declares a property 'encoded' when a classifier on hidden states achieves high accuracy. The protocol works well on a snapshot
arXiv:2606.09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performan
arXiv:2502.11034v3 Announce Type: replace Abstract: Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause
arXiv:2606.10722v1 Announce Type: new Abstract: We study dense-to-sparse continual training as a way to construct channel-sparse large language models from dense checkpoints. Starting from a Qwen2.5-8
arXiv:2606.10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge-intensive question answering. However, existing a
arXiv:2603.09979v2 Announce Type: replace Abstract: Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez are frequently quoted, paraphrased,
arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca
arXiv:2606.09852v1 Announce Type: cross Abstract: High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainabil
arXiv:2606.09879v1 Announce Type: new Abstract: This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy
arXiv:2602.12966v2 Announce Type: replace Abstract: Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall beh
arXiv:2606.10346v1 Announce Type: new Abstract: Reinforcement learning has become a key paradigm for eliciting reasoning abilities in large language models, where exploration is crucial for discoverin
arXiv:2606.10359v1 Announce Type: new Abstract: AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforc
arXiv:2606.10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering. Existing approaches typically rely on a separate mo
arXiv:2606.09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Large Language Models (LLMs), but activation quantiza
arXiv:2606.09866v1 Announce Type: cross Abstract: Fine-tuning safety aligned large language models (LLMs) on downstream data improves adaptation but may erode learned safety behavior. Existing methods
arXiv:2606.10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often stu
arXiv:2606.08081v1 Announce Type: cross Abstract: Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific conventions grounded in s
arXiv:2606.08761v1 Announce Type: cross Abstract: W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed
arXiv:2606.07853v1 Announce Type: cross Abstract: Large Language Models are transforming the support for clinical decision and their application in real scenarios. Yet, most benchmarks are conducted i
arXiv:2606.09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call brain-pro
arXiv:2509.25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large languag