Knowledge catalogue
arXiv:2505.01458v2 Announce Type: replace-cross Abstract: Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, ti
arXiv:2606.11150v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experime
arXiv:2606.10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-conc
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:2606.10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privac
arXiv:2606.10381v1 Announce Type: cross Abstract: Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a r
arXiv:2606.10577v1 Announce Type: new Abstract: Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs). Howe
arXiv:2606.10903v1 Announce Type: new Abstract: Monocular local navigation is attractive for lightweight robots, but existing vision-based policies often couple perception to a specific body, camera h
This article from Latent Space discusses Anthropic's Claude Fable 5 model, examining its capabilities in handling creative and mythological content while maintaining safety guardrails, along with cove
arXiv:2606.09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measu
arXiv:2606.10686v1 Announce Type: cross Abstract: The pulsar magnetosphere has only recently been addressed using Physics-Informed Neural Networks (PINNs), by deploying a domain-decomposition approach
arXiv:2603.14463v2 Announce Type: replace Abstract: Adapting Large Language Models (LLMs) to high-stakes vertical domains like insurance presents a significant challenge: scenarios demand strict adher
and the video for reference: https://x.com/ClaudeDevs/status/2064399512664526853 (I didnt get to use the updated designs in time) Claude Fable 5 changed how we work on the Claude Code team day to day.
Announcing the Gemma challenge! Google, Hugging Face, and the open-source AI community choose to empower AI builders rather than sabotage them. Fun to see the Hub becoming the platform where agents co
arXiv:2606.09942v1 Announce Type: cross Abstract: Microservice systems are widely used to build cloud applications, yet their complexity makes failures inevitable, degrading user experience and causin
Maxwell Zeff / Wired: Anthropic backtracks on a policy limiting Claude Fable 5's ability to develop other AI models, after significant backlash from the AI research community — The company changed cou
Dean W. Ball / @deanwball: Anthropic secretly limiting Claude's usefulness for LLM development strengthens the argument that Anthropic is using AI safety to justify monopolistic behavior — My last obs
As believers of open research, we are disappointed to see Anthropic silently degrading Fable 5 for AI development 'Any topic related to building pretraining pipelines, distributed training infrastruct
arXiv:2602.04935v3 Announce Type: replace-cross Abstract: Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy t
arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effec
arXiv:2505.23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization wi
Thariq posted about attending a coding event or workshop featuring Claude in Tokyo and invited others to say hello if they encountered him there. The post appears to be a social announcement about his
arXiv:2606.11052v1 Announce Type: new Abstract: Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-con
arXiv:2606.10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich conte
arXiv:2606.10156v1 Announce Type: cross Abstract: As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benc
arXiv:2407.20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language und
arXiv:2606.10281v1 Announce Type: cross Abstract: This paper presents AuditBench, a new benchmark dataset for evaluating the capabilities of LLMs at investigating security-related system audit logs. W
arXiv:2606.10554v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications that require access to up-to-date knowledge. However, retraining LLM
arXiv:2606.10364v1 Announce Type: new Abstract: Reconstructing printable 3D models from Mars rover imagery is challenging because Martian terrain is low-texture, irregular, and partially observed. We
arXiv:2606.10061v1 Announce Type: new Abstract: Large language models (LLMs) increasingly participate in emotionally sensitive social conversations, where responses may shift from balanced support tow
arXiv:2606.10803v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) excel at utilizing digital APIs and increasingly serve as the 'brain' of embodied AI, instructing robots to i
arXiv:2603.21350v2 Announce Type: replace Abstract: Epistemic reasoning requires agents to infer the state of the world from partial observations and information about other agents' knowledge. Prior w
arXiv:2606.10905v1 Announce Type: new Abstract: Visual in-Context Learning (VICL) aims at making progress towards adaptive vision models, that can -- based on a few examples -- adapt to a new task at
arXiv:2606.10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes. Leading recipes (RLVR, group-rel
arXiv:2502.01272v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks. However, recent studies have highlig
arXiv:2602.21331v2 Announce Type: replace Abstract: General-purpose simulators have accelerated the development of robots. Traditional simulators based on first-principles, however, typically require
arXiv:2606.10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly und
arXiv:2606.09854v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect pee
arXiv:2606.10640v1 Announce Type: new Abstract: In this report, we present our champion solution for the DataMFM Challenge Track 2: Chart Understanding. This track requires models to recover structure
arXiv:2606.11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This part
arXiv:2606.10798v1 Announce Type: new Abstract: Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series. However, existing TSFMs often incur high co
Claude Fable 5 is now available in Computer as an orchestrator model designed by Anthropic for handling long and complex tasks. This represents Anthropic's latest state-of-the-art model offering enhan
Claude Fable 5 thinks document parsing is beneath it It is absolutely crushing on all reasoning-intensive/long horizon benchmarks: SWE-Bench Pro, FrontierCode, GDPval, Runescape, etc. But for document
Anthropic just released Claude Fable 5, calling it the most powerful AI model it has ever made widely available and praising its skills in biology, among others. But the model won't answer basic biolo
arXiv:2505.11034v2 Announce Type: replace-cross Abstract: Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, lim
arXiv:2606.10935v1 Announce Type: cross Abstract: Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass. Multi-token prediction (MTP)
arXiv:2606.10673v1 Announce Type: cross Abstract: Although some very common test beds exist for assessing the performance of clustering methods, large scale benchmarking is typically limited to relati
arXiv:2606.10401v1 Announce Type: new Abstract: Spatial intelligence is a key frontier for multimodal large language models (MLLMs), enabling them to reason about the physical world from visual experi
arXiv:2606.10087v1 Announce Type: new Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative f
Cohere has released Transcribe, an open-source speech recognition model that achieved the top ranking on Hugging Face's newly established Far-Field Automatic Speech Recognition (ASR) benchmark. The mo
arXiv:2606.09833v1 Announce Type: cross Abstract: AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration b
arXiv:2606.10479v1 Announce Type: new Abstract: Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structu
arXiv:2601.18026v2 Announce Type: replace Abstract: Language identification (LID) is a fundamental step in curating multilingual corpora. However, LID models still perform poorly for many languages, e
arXiv:2606.09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model. We pre
arXiv:2510.04195v2 Announce Type: replace Abstract: Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries
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:2606.10050v1 Announce Type: cross Abstract: Traditional UV unwrapping relies on direct optimization of geometric distortion energies and can fail through invalid initialization, local minima, or
arXiv:2606.10842v1 Announce Type: new Abstract: We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top
arXiv:2504.02323v4 Announce Type: replace Abstract: Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various
Lorenzo Franceschi-Bicchierai / TechCrunch: Cybersecurity researchers complain that Claude Fable's guardrails are too strict, rejecting “innocuous tasks” like reading blog posts or performing code rev