Knowledge catalogue
arXiv:2601.16333v3 Announce Type: replace Abstract: Foundation models are used for many real-world applications involving language understanding and generation from temporally-ordered multimodal event
arXiv:2610.17709v1 Announce Type: new Abstract: Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset
arXiv:2610.17285v1 Announce Type: new Abstract: Modern neural-network training uses mixed recipes, assigning AdamW-like or sign-based updates to embedding and output layers and spectral updates to hid
arXiv:2610.18294v1 Announce Type: new Abstract: Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent trainin
arXiv:2610.17806v1 Announce Type: new Abstract: Collision rate remains a dominant metric for evaluating autonomous driving trajectory safety, but its binary nature obscures substantial safety differen
arXiv:2610.18842v1 Announce Type: cross Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive S
arXiv:2610.15778v1 Announce Type: new Abstract: When a policy is trained with GRPO against a frozen, reference-free LLM judge, the judge accepts more of its answers, but in a post-hoc analysis we dete
arXiv:2610.14530v1 Announce Type: new Abstract: Multi-robot systems (MRS) offer significant advantages over single-robot platforms by enabling information sharing and coordination for different tasks
arXiv:2610.16152v1 Announce Type: new Abstract: Although post-training significantly enhances model performance, the use of massive undisclosed data raises concerns about benchmark contamination and c
arXiv:2610.17355v1 Announce Type: new Abstract: Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decod
arXiv:2606.18097v2 Announce Type: replace Abstract: Deformable Linear Objects (DLOs), such as wires and cables, are central to industrial assembly. Unlike rigid objects, whose state is captured by a 6
arXiv:2610.15299v1 Announce Type: new Abstract: Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) still i
arXiv:2610.18067v1 Announce Type: cross Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require furthe
arXiv:2610.15429v1 Announce Type: new Abstract: How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce Spe
arXiv:2610.17434v1 Announce Type: new Abstract: Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual
arXiv:2610.14861v1 Announce Type: new Abstract: Time-series forecasting plays a vital role in a wide range of real-world applications. Recent approaches have achieved strong performance by modeling te
arXiv:2610.18826v1 Announce Type: cross Abstract: We introduce WorldOracle, a benchmark specifically designed to evaluate action-conditioned world models (ACWMs) against paired real-world executions.
arXiv:2610.18846v1 Announce Type: new Abstract: Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly
arXiv:2610.16337v1 Announce Type: new Abstract: Rotary Positional Embedding (RoPE) is widely used to encode relative positions in Transformers. In multi-view settings, however, patch coordinates are d
arXiv:2610.17922v1 Announce Type: new Abstract: Action-conditioned world models can reduce costly real-robot interaction in reinforcement learning for Vision-Language-Action models (VLA-RL), but hallu
arXiv:2610.15394v1 Announce Type: new Abstract: Structured pruning is typically formulated as identifying which model dimensions to remove, often within the model's original representation. However, t
arXiv:2610.16811v1 Announce Type: new Abstract: Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition
arXiv:2610.16478v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for vision-based autonomous driving, but policies trained in simulation often suffer severe per
arXiv:2610.16131v1 Announce Type: new Abstract: Financial forecasting has traditionally relied on numerical time-series (TS) signals, while textual information such as news remains largely underutiliz
You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomo
arXiv:2610.14802v1 Announce Type: new Abstract: End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a v
Lauren Forristal / TechCrunch: YouTube Music rolls out labels for songs created with the help of AI; Spotify has AI labels, and Apple Music plans to add “Made With AI” labels later this year — YouTube
arXiv:2610.17521v1 Announce Type: new Abstract: Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable evalu
arXiv:2610.15225v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs). However, ZO optimization suffers from high variance
arXiv:2610.15336v1 Announce Type: new Abstract: Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugg
arXiv:2610.17696v1 Announce Type: new Abstract: Identifying protein-ligand binding sites (pockets) is important for understanding protein function and developing drugs. However, no public method has l
1) Trying again. TLDR: Everyone can win. Open-source, frontier labs, infrastructure, applications and most importantly the American people. I understand all of the jitters about Anthropic losing share
1M-token, multimodal decision models are here! But there is more to this one. You can classify, extract, and summarize with 1M tokens of text and image input. ScaleDown's Constrained Decoding Models r
Here is how i serve 40 people (10 of them developers) with local AI services. n8n for automatisation whisper and Vexa AI, a bot joins Teams and makes transcripts, n8n later extracts decisions and todo
A gap that has been fixed in our methodology that highlighted a decline was not including local models (GGUF, AWQ, ONNX, etc). Earlier, these were far harder to track and closer to a rounding error. N
Financial Times: A global chip stock sell-off deepens after Broadcom's CEO likened AI investing to a casino, with Samsung down as much as 8.8%, SK Hynix down 9.2%, and Micron 4% — Declines for Samsung
The Information: A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique — OpenAI is grappling w
A worthwhile (and unnerving) reminder from Anthropic that we should be paying attention to AI ability thresholds, not just steady climbs In this case, the threshold is the capability needed for a self
After much testing and talking to actual users across all three proactive AI agents: Muse - best one for your parents, heavy IG/FB users, people who like or need easy setups, people who don’t want to
NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip. With up to 128GB of
Follow-up to last week's post about streaming MoE experts from disk in a browser tab. That ran on hand-written engines for two models. This week the same disk tier sits under llama.cpp's own WebGPU ba
and livestream now https://x.com/aidotengineer/status/2109994269800808626?s=46 Live from New York: AI Engineer NYC! https://www.youtube.com/live/akEqiXFo3GM - @Bridgewater Head of Product Eng - @Anthr
🔎 Announced at Interrupt: AI Search in LangSmith You used to need an evaluator or read hours of conversations to find traces that answer questions such as: 💬 Does the user seemed frustrated?' 💬 Where
Jack Clark / Import AI: Anthropic co-founder Jack Clark says “I now think it's more likely we'll see full RSI become possible in 2027”, earlier than his previous prediction of 2028 — Will we give robo
Anthropic: Anthropic details Scion, a git replacement for its monorepo, built by seven engineers with Claude in five months, as daily merges rose from 2.5K in May to 30K+ — As our merges per day grew
🚨 @AnthropicAI: AI “MAY BE” capable of self-replicating! Now read the actual research: • No fully autonomous rogue replicator demonstrated. • Cyber exploitation deliberately simplified. • Real-world r
I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since
I've been reading about all these modders using AI to reverse-engineer games and software. I've been trying out photocraft and gridcraft and have just watched a GTA5 mod featuring Sonic. It's pretty d
Learn how Azure Content Understanding prebuilt analyzers combine domain knowledge with grounding and confidence, and what Advanced Contextualization preview benchmarks show about quality, modeled cost
hexagon: extend scalar DMA broadcasting support for binary ops (#30245) tests: cover weighted scalar broadcasts Assisted-by: OpenCode ggml : support extended scalar DMA binary ops Assisted-by: OpenCod
models : remove redundant ggml_cont calls now supported by all unary kernels (#30198) models: remove redundant ggml_cont calls now supported by CUDA unary kernels models: restore cont_2d after sigmoid
ggml-zdnn : introduce Q8_0 mat mul (#29836) ggml-zdnn: initial prototype of q8_0 matmul Signed-off-by: Aaron Teo aaron.teo1@ibm.com docs: update zdnn docs Signed-off-by: Aaron Teo aaron.teo1@ibm.com S
graph : avoid reallocations in the 'no cache' path (#30439) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/55354972 macOS/iOS: macOS Apple Silicon (arm64)
cuda : warnings cleanup Signed-off-by: Adrien Gallouët angt@huggingface.co Update ggml/src/ggml-cuda/common.cuh Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Signed-off-by: Adrien
cuda : add GGML_CUDA_GRAPH_DEBUG and read env vars once (#30327) ggml-cuda: gate CUDA graph debug logs behind GGML_CUDA_GRAPH_DEBUG ggml-cuda: cache env var lookups in static const instead of re-readi
vulkan: allow multiple devices to access gpu-visible host memory (#29741) vulkan: allow multiple devices to access gpu-visible host memory clean up erroneous newlines add Windows support handle nullpt
tests : consolidate context state tests into test-llama-context (#30023) tests : consolidate the context state tests into test-llama-context test-save-load-state, test-recurrent-state-rollback and tes
graph: skip the LM head for pooled embeddings (#30445) graph: skip the LM head for pooled embeddings A context that extracts pooled embeddings outputs one vector per sequence, but every model still ex
model: load YaRN beta metadata for laguna models (#30331) Assisted-by: Codex Co-authored-by: Adam Caldwell accaldwell@users.noreply.github.com Website: https://llama.app Attestations: https://github.c
llama : do not map foreign ranges into a backend buffer A buffer created from a host pointer pins everything that it wraps. When several contexts share the same file (lazy tensors, MoE tensors kept on