Knowledge catalogue
arXiv:2608.05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: p
Following up on yesterday's post about running everyone's faves on 2 x 16gb cards while maximizing performance and KV. Previous post data used abandoned Cu130 VLLM image. Stats here are done on cu129-
The tweet is a question from user Simon Willison (posted on 6 Aug 2026) asking which OpenAI API model corresponds to the ChatGPT “GPT‑5.6 Instant” version. No answer or clarification is included in th
TL;DR: On a Qwen3.6-35B-A3B Q6 setup sized for 64K context on a 24GB RTX 3090, spilling eight MoE expert layers to CPU freed enough VRAM to increase -b from 512 to 1024 and -ub from 128 to 512. Prompt
arXiv:2608.05042v1 Announce Type: new Abstract: Leveraging pre-trained vision-language models (VLMs) to construct vision-language-action (VLA) models has emerged as a promising paradigm for 3D robot m
arXiv:2608.04746v1 Announce Type: new Abstract: LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures t
arXiv:2608.05149v1 Announce Type: new Abstract: Current instruction-based image retrieval systems are powerful but limited to single-turn interactions, failing to capture the iterative nature of compl
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such a
arXiv:2511.17354v4 Announce Type: replace Abstract: Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for lear
arXiv:2507.10599v3 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for
arXiv:2608.04368v1 Announce Type: new Abstract: Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to ineffici
arXiv:2608.04439v1 Announce Type: cross Abstract: Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated al
arXiv:2608.04765v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However,
arXiv:2608.04404v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot manipulation by learning how the environment evolves beyond the current observation. However, existing approach
arXiv:2601.03808v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handle
arXiv:2608.04018v1 Announce Type: cross Abstract: AI agents are increasingly embedded in organizational workflows, where they interact with external information sources and invoke digital tools to per
arXiv:2603.12408v3 Announce Type: replace-cross Abstract: Motion imitation learning (IL) is increasingly used in robotics and human gait modeling, yet its ability to recover biomechanically consistent
arXiv:2608.04505v1 Announce Type: new Abstract: This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward glo
Link to the article: KV Cache Quantization Benchmarks: KVarN, Precision Tail KLD benchmarks with BeeLlama.cpp v0.4.0, fork of llama.cpp with more KV cache quantization options. Models: Qwen 3.6 27B Q5
arXiv:2608.02347v2 Announce Type: replace Abstract: Recurrent linear attention models (RLAs) such as Mamba offer efficient linear-time sequence modeling as an alternative to Transformers, yet their fi
arXiv:2606.17188v3 Announce Type: replace-cross Abstract: Current multilingual evaluations for Vision-Language Models (VLMs) assume a one-to-one mapping between language and orthography, overlooking b
arXiv:2608.05049v1 Announce Type: new Abstract: Instruction-based video editing (IVE) is an emerging field with broad applications, yet evaluating editing models remains challenging. Existing benchmar
arXiv:2608.04255v1 Announce Type: cross Abstract: Graph inference over relational data can expose sensitive edge information, and this risk becomes more severe in dynamic graphs, where repeated model
arXiv:2508.14006v2 Announce Type: replace Abstract: We introduce ResPlan, a dataset of 17,000 residential floor plans with vector geometry, room-connectivity graphs, and metric-scale coordinates. Each
arXiv:2607.21597v2 Announce Type: replace Abstract: Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event
arXiv:2608.04289v1 Announce Type: new Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitm
arXiv:2608.04075v1 Announce Type: cross Abstract: Accurate traffic forecasting is essential for proactive resource management in edge computing, where service demand evolves dynamically across both sp
arXiv:2603.03589v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new t
arXiv:2608.04676v1 Announce Type: new Abstract: Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for
arXiv:2608.04930v1 Announce Type: cross Abstract: Bayesian causal discovery seeks to determine the posterior distribution of causal theories, which are interpreted as directed acyclic graphs (DAGs) th
arXiv:2608.04698v1 Announce Type: cross Abstract: We tackle the challenging yet underexplored task of Generalized Referring Expression Comprehension (GREC), which requires a model to localize the obje
arXiv:2608.04611v1 Announce Type: cross Abstract: Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable
arXiv:2508.12480v3 Announce Type: replace Abstract: The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZS
arXiv:2608.04260v1 Announce Type: new Abstract: Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require r
arXiv:2608.04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost
arXiv:2508.04780v2 Announce Type: replace-cross Abstract: The increasing frequency of extreme weather events, such as hurricanes, highlights the urgent need for efficient and equitable power system re
arXiv:2409.02228v2 Announce Type: replace-cross Abstract: When language models (LMs) are trained to forget (or 'unlearn'') a skill, how precisely does their behavior change? We study the behavior of t
arXiv:2608.04902v1 Announce Type: new Abstract: Video-to-audio (V2A) generation extends image-to-audio generation (I2A) by introducing consecutive frames that provide essential temporal cues for audio
arXiv:2608.02805v1 Announce Type: cross Abstract: In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-for
After rigorous testing, our joint AI project with Daiwa Securities is entering the full-scale production phase. We're bringing our agentic AI systems to @Daiwa_JP’s wealth management teams to accelera
Most agent memory setups run a model call on the way in. Something reads the turn, decides whether it's worth keeping, rewrites it into a 'memory', tags it with a type and an importance score. That's
arXiv:2601.19138v2 Announce Type: replace-cross Abstract: Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security asse
arXiv:2608.03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much pro
arXiv:2608.02941v1 Announce Type: new Abstract: We audit five frontier large language models on native Bangla derogatory speech (gali) across six protocols to test a single hypothesis: Comprehension-C
arXiv:2608.03898v1 Announce Type: new Abstract: The automatic structural analysis of legal texts is a cornerstone of legal technology, yet the extraction of their logical components remains a signific
There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multipl
arXiv:2608.03800v1 Announce Type: cross Abstract: An LLM-based agent is a loop that reads itself. Agentic frameworks externalize identity, memory, and disposition into editable files. The agent loads
arXiv:2608.03340v1 Announce Type: new Abstract: Predicting LLM's capabilities on real-world tasks is essential, yet the extent to which performance on commonsense benchmarks predicts downstream perfor
arXiv:2608.02955v1 Announce Type: cross Abstract: This research paper describes an exploratory study on the effectiveness of Chat Debugging: troubleshooting malfunctioning analog circuits on breadboar
arXiv:2608.03147v1 Announce Type: new Abstract: Referring Remote Sensing Image Segmentation (RRSIS) has achieved significant progress through the integration of VLMs and the Segment Anything Model (SA
arXiv:2608.02663v1 Announce Type: cross Abstract: Accurate ICU mortality prediction requires modeling irregular clinical observations across heterogeneous entity types. Existing sequence models handle
arXiv:2608.03591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to
arXiv:2608.03025v1 Announce Type: new Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual ev
arXiv:2608.03177v1 Announce Type: new Abstract: How can question answering (QA) systems determine whether a query is ambiguous? Ambiguity detection is essential in open-domain QA, as misclassification
arXiv:2608.03794v1 Announce Type: cross Abstract: Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administra
arXiv:2608.02919v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-
arXiv:2608.03605v1 Announce Type: new Abstract: Federated fine-tuning with Low-Rank Adaptation (LoRA) enables efficient collaborative adaptation of Large Language Models (LLMs) without centralizing pr
arXiv:2608.03071v1 Announce Type: new Abstract: Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool
arXiv:2608.03064v1 Announce Type: new Abstract: We study open-vocabulary 3D indoor layout generation, which synthesizes diverse and physically plausible scenes from unlabeled 3D assets using free-form
arXiv:2608.03966v1 Announce Type: new Abstract: Large language models can generate fluent Arabic answers while introducing factual errors that are difficult to identify and verify. Existing Arabic hal