Knowledge catalogue
arXiv:2608.25601v1 Announce Type: new Abstract: Multi-camera systems are foundational to modern media production, and multi-camera editing is a critical task. This involves the proper selection of the
arXiv:2411.17629v3 Announce Type: replace Abstract: Motivation: Organic synthesis is fundamental to the chemical industry, particularly in domains such as pharmaceutical development. While artificial
arXiv:2608.25893v1 Announce Type: new Abstract: Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single ca
A great deep dive from the @fal team on how they built H3 Max, combining post-training with a co-designed inference stack to improve prompt adherence, visual quality, and speed. We're proud to see Min
arXiv:2608.25592v1 Announce Type: cross Abstract: Inorganic solid-state electrolytes must combine high room-temperature ionic conductivity, a wide electrochemical window, excellent electronic insulati
arXiv:2606.19660v2 Announce Type: replace-cross Abstract: Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applicatio
arXiv:2608.24935v1 Announce Type: new Abstract: Accurate identification of early-stage apple fruitlet anatomical structures, including the calyx, fruitlet body, and peduncle, is essential for robotic
arXiv:2608.25388v1 Announce Type: cross Abstract: We describe a systematic approach for spawning and aggregating multi-class cryo-EM reconstruction jobs. This approach formalizes standard ad hoc strat
J'utilise souvent MiniMax H3 avec des images de référence ; je voulais essayer une vidéo que j'avais créée avec Wan (la version plus ancienne), mais cette fois en utilisant seulement une invite (un LL
arXiv:2608.25498v1 Announce Type: cross Abstract: Accurate online traffic prediction is essential for intelligent transportation systems, where forecasting must be performed continuously under imperfe
arXiv:2608.25022v1 Announce Type: new Abstract: As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such mod
arXiv:2608.26008v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, an
arXiv:2608.25940v1 Announce Type: new Abstract: Physical AI models are evaluated on suites of benchmarks that differ across model reports, leaving the model-by-benchmark matrix sparse and the relation
arXiv:2608.25489v1 Announce Type: cross Abstract: Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and expos
arXiv:2608.25395v1 Announce Type: new Abstract: Recent vision-language-action models offer a path toward robots with broader repertoires than conventional task-specific systems. Construction deploymen
arXiv:2608.25547v1 Announce Type: new Abstract: To apply the techniques of embodied artificial intelligence to human-oid robots for complex manipulations, dexterous robotic hands are indispensable, wh
arXiv:2608.25643v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss alloc
Jack Queen / Reuters: A US judge blocks the Pentagon from blacklisting Anthropic, ruling that its designation as a supply-chain risk was “illegal and baseless” — A U.S. judge on Thursday blocked the P
arXiv:2608.26095v1 Announce Type: new Abstract: In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from s
arXiv:2608.25315v1 Announce Type: new Abstract: Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions
arXiv:2607.09156v2 Announce Type: replace Abstract: Additive activation steering is calibrated in single-turn chat and then deployed inside agent scaffolds. The quantity usually reported for that move
arXiv:2607.08789v2 Announce Type: replace Abstract: Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such updat
arXiv:2608.25524v1 Announce Type: cross Abstract: The Levenberg-Marquardt (LM) algorithm is the most widely used method for solving nonlinear least-squares problems, as it combines the robustness of s
arXiv:2608.25513v1 Announce Type: cross Abstract: Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle lear
arXiv:2608.25379v1 Announce Type: new Abstract: Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning and create a failure mode that final-an
arXiv:2608.25412v1 Announce Type: new Abstract: Multi-vector representations have emerged as an effective paradigm for multimodal retrieval, representing each sample with multiple complementary embedd
arXiv:2608.25559v1 Announce Type: new Abstract: Video deep research answers complex questions by jointly understanding video content and retrieving external knowledge from the open Web. However, diver
arXiv:2604.05876v2 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) in real-world dynamic environments raises the challenge of updating their pre-trained knowledge. While existi
arXiv:2312.10089v2 Announce Type: replace Abstract: Content-based image retrieval (CBIR) systems have emerged as crucial tools in the field of computer vision, allowing for image search based on visua
arXiv:2608.25610v1 Announce Type: new Abstract: Robot policies are predominantly learned with classical parametric variants of imitation learning or RL, where training stores the agent's behavior excl
arXiv:2608.25681v1 Announce Type: new Abstract: Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial
arXiv:2608.25477v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) is a promising 6G paradigm, but dynamic multi-UAV ISAC control must
arXiv:2608.24954v1 Announce Type: new Abstract: Large language models (LLMs) hallucinate numerical values when generating high-stakes meteorological text, posing risks for weather communication. We pr
Everything has changed in two months: DS4 0731 flash was the start of a wave that is taking open weights to paradise. It is easy to think that Qwen 4 and GLM 6 will be on par with Mythos. submitted by
arXiv:2608.26093v1 Announce Type: new Abstract: Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe
arXiv:2608.25799v1 Announce Type: new Abstract: Orchards form semi-structured environments in which parallel tree rows create natural driving corridors, yet narrow inter-row clearance and dense foliag
arXiv:2507.18538v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral to the 5G Radio Access Network (RAN), enabling beam manag
arXiv:2510.15987v3 Announce Type: replace Abstract: How do inference time and latent computations enable large language models (LLMs) to solve multi-step reasoning problems? We introduce AlgoTrace, a
arXiv:2604.03403v2 Announce Type: replace-cross Abstract: Dense retrieval systems increasingly face an asymmetry between complex instruction-like queries and relatively simple, static document collect
In an open letter signed by over 100 tech firms—including Anthropic, AWS, Google, Microsoft, OpenAI, and Oracle—the authors warn that AI‑driven cyber attacks will soon become far more sophisticated an
arXiv:2608.25869v1 Announce Type: new Abstract: Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter
Anthropic: Anthropic releases findings from a pilot that let three external researchers run studies on Claude usage; one study found users delegate high-stakes tasks — Earlier this year, we ran a pilo
Will Knight / Wired: Anthropic releases Model Hardware Standard, a framework to help AI agents use physical systems like microscopes, quantum computing hardware, and robot arms — The potential for AI
On Thursday, a judge ruled that the Pentagon's blacklisting of Anthropic earlier this year was unconstitutional, delivering the AI lab a win in a monthslong rollercoaster of a battle with the Trump ad
arXiv:2608.25830v1 Announce Type: new Abstract: Global Tensor Motion Planning (GTMP) solves motion planning with batched tensor operations over a layered multipartite graph. We generalize GTMP so that
arXiv:2608.25089v1 Announce Type: new Abstract: Crosslingual evaluation of language models that enables fair comparisons remains a fundamental challenge in multilingual NLP. Existing studies adopt a v
arXiv:2608.25727v1 Announce Type: new Abstract: Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving ris
arXiv:2510.20803v2 Announce Type: replace Abstract: We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level pe
arXiv:2608.25520v1 Announce Type: new Abstract: Audio-visual cross-modal Fine-Grained Visual Categorization (FGVC) aims to identify fine-grained categories by jointly leveraging visual and auditory in
arXiv:2608.26004v1 Announce Type: cross Abstract: Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control laten
audio.cpp 0.7 is out :) This release adds a lot of new audio models and a new way to compare them locally. Audio.cpp is now at 62 model families and 85+ model variants. And it keeps growing! The bigge
arXiv:2608.25948v1 Announce Type: new Abstract: Medical image foundation models can predict clinical phenotypes from computed tomography (CT), but strong performance leaves open whether they read dise
// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a
arXiv:2608.25465v1 Announce Type: new Abstract: Visual inspection of welded assemblies remains one of the least automated stages in many industrial production processes, still depending largely on the
arXiv:2608.25637v1 Announce Type: new Abstract: Reference-based verifiers are important for evaluating reasoning models and providing accurate outcome rewards in reinforcement learning with verifiable
arXiv:2608.25618v1 Announce Type: new Abstract: Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working
hexagon: support for multi-NPU devices (IQ9, IQ10) and fully asynchronous backend (#26501) hexagon: use non-host bufs by default and make the backend fully async hex-hb: remove optional hostbuf suppor
models : support nanbeige4.2-3B (#27730) Co-authored-by: admin lizongqiang@kanzhun.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43308396 macOS/iOS: m
llama : add --n-cpu-ffn option (#26622) common : dedupe --n-cpu-moe / --spec-draft-n-cpu-moe override loops common : add --n-cpu-ffn to CPU-offload dense FFN weights of first N layers common : general
metal : fix memory leaks due to missing autoreleasepools (#27758) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43372015 macOS/iOS: macOS Apple Silicon (a