Knowledge catalogue
arXiv:2609.18525v1 Announce Type: new Abstract: Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses
arXiv:2609.17984v1 Announce Type: new Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by reca
Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, with 3.2× end-to-end throughput along the way. What I keep th
arXiv:2411.01289v2 Announce Type: replace Abstract: Complex events originate from other primitive events combined according to defined patterns and rules. Instead of using specialists' manual work to
Anyone else trying out the new Union stealth model on openrouter? It’s pretty good for a free model, and of course I had to run tokenizer tests and training cutoff tests which established it’s the 99%
I posted something about a 9b model a few days ago. The real problem was 2 fold. Someone suggested the size was too big to prove it all out. It's a fair argument. I needed the model depth though. The
What's Changed Added first-run setup when running ollama, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. Added ollama://apps to open
The decode loop releases MLX's pool of freed buffers every 256 generated tokens, which is also how often the KV cache grows and drops its previous, smaller buffers. The check fires only when the token
arXiv:2602.00408v3 Announce Type: replace-cross Abstract: This paper proposes a novel Variational Graph-to-Scheduler (VG2S) framework for solving the Job Shop Scheduling Problem (JSSP), a critical tas
arXiv:2609.18769v1 Announce Type: new Abstract: Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document i
arXiv:2609.18077v1 Announce Type: cross Abstract: Open-source video generative models ship almost exclusively as PyTorch/CUDA reference implementations. This leaves Cloud TPU pods without a production
arXiv:2609.18302v1 Announce Type: new Abstract: RAW-to-sRGB image signal processing (ISP) must recover perceptually faithful colors and fine details from sensor measurements, often under imperfect spa
arXiv:2609.18663v1 Announce Type: cross Abstract: Billion-parameter vision--language--action (VLA) policies demand substantial onboard power, while communication delays in remote inference hinder time
arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing bench
VQ-bench is an open‑source framework that lets researchers construct vector quantization schemes from a small set of reusable primitive operations, enabling easy comparison of different methods on the
arXiv:2609.18812v1 Announce Type: new Abstract: Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outpu
We've been tuning vLLM/SGLang/llama.cpp setups for a long time and got tired of the profiling part: nsys trace, open the GUI, squint, change a flag, repeat. The profilers assume a human is looking at
arXiv:2609.18435v1 Announce Type: new Abstract: Automating biological research requires general-purpose, reproducible robot systems that allow individual wet-lab researchers to delegate robot tasks wi
What makes Claude Projects so interesting is that it handles teams of agents really well, you talk to a main orchestrator agent and it spins up specialists. Basically it creates an organization to sol
arXiv:2606.15121v3 Announce Type: replace Abstract: Predicting the timing of individual and collective panic emotional arousal before manifestation is essential for timely emergency intervention. Exis
arXiv:2609.18283v1 Announce Type: new Abstract: As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large langua
arXiv:2609.18731v1 Announce Type: new Abstract: Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like P
arXiv:2609.17857v1 Announce Type: cross Abstract: Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four
Who need words any more Words are just human kludge AI don’t need no words We release Needle 3: A Sliceable 8-29MB automation foundation model that can match DeepSeek V4 Flash. One set of weights, eve
Hey guys, really wondering now why we got (SOTA or at least good enough) open weights on nearly every use case, like LLMs, T2I (Krea2), music (Yue2), video generation (Minimax H3), but not image edit?
arXiv:2609.17810v1 Announce Type: new Abstract: Monocular reconstruction of wind-driven vegetation is severely underconstrained: motion along the viewing direction is largely unobservable, a moving ca
arXiv:2609.19006v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Large Reasoning Models (LRMs) are typically evaluated on challenging benchmarks through dataset accuracy alone, provi
I find another new model at HF: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B 'Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by Chin
arXiv:2609.18772v1 Announce Type: new Abstract: Sign language processing advances rapidly for high-resource languages such as American Sign Language (ASL), yet most of the world's sign languages lack
arXiv:2609.16067v1 Announce Type: new Abstract: In order to solve the high-dimensional (d geq 30) expensive black-box problems within budget, an efficient global optimization (EGO) algorithm with a dy
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with
arXiv:2609.16199v1 Announce Type: cross Abstract: This article describes an open image dataset for developing and evaluating active-fire segmentation methods in satellite imagery. The dataset contains
arXiv:2609.17171v1 Announce Type: cross Abstract: The interpretability of complex machine learning models is of paramount importance, especially in real-world high-stakes domains such as healthcare an
arXiv:2609.16824v1 Announce Type: new Abstract: Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays
arXiv:2609.16309v1 Announce Type: new Abstract: Despite the rapid progress of LLM-based agents for planning, code generation, and debugging, their practical value for tabular machine learning remains
arXiv:2609.17119v1 Announce Type: new Abstract: Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's beh
Anthropic PBC said today it’s trying to make life simpler for its customers by merging its regular chatbot Claude with its agentic artificial intelligence tool Claude Cowork. The merger, which went in
Ivan Mehta / TechCrunch: Anthropic merges Claude chat and Cowork, and adds a feature for making presentations and documents, rolling out to Pro and Max plans first — Anthropic is merging its front-end
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that p
arXiv:2609.16075v1 Announce Type: cross Abstract: Flexible robotic production requires joint decisions on process progression, material routing, resource assignment, temporary cooperation, and simulta
arXiv:2609.16302v1 Announce Type: cross Abstract: When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and
arXiv:2609.16573v1 Announce Type: new Abstract: Multi-modal spatio-temporal forecasting (MM-STF) supports weather nowcasting, traffic prediction, and earth-system modeling by combining heterogeneous s
arXiv:2609.16793v1 Announce Type: cross Abstract: People increasingly reason with large language models (LLMs), yet complementary capabilities do not guarantee outperforming both components. In a betw
llama-bench: support --version to print build info (#28971) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47831792 macOS/iOS: macOS Apple Silicon (arm64)
ci : add self-hosted webgpu to hf-jobs (#28712) add self-hosted vulkan and webgpu to hf-jobs try t4-medium cont : adjust cpu backend threads try t4-small again restore cm jobs Co-authored-by: Georgi G
metal: fix NaN in mul_mm_id when activations exceed f16 range (#26223) test-backend-ops: reproduce MUL_MAT_ID NaN for activations beyond f16 The Metal mul_mm_id path narrows src1 to half for the simdg
vulkan: make MUL_MAT_ID BN/2 tail unconditional (#28923) Use BN/2 as the default for BNover2 and as the disabled fallback for BNover4, and remove the enable gate from the MUL_MAT_ID BN/2 branch. The B
chat : force n</think> on reasoning budget end for qwen3-coder (#28869) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47858837 macOS/iOS: macOS Apple Sili
HIP: broaden MoE ncols_opt tile heuristic on RDNA3.5 architecture (#28935) It's found the MoE ncols_opt tile heuristic needs to be broadened to include the RDNA3.5 architecture. The code change is imp
qwen4exp: add hc ops (#28901) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47897353 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, Kl
Change max context length for auto-fitting with unified KV (#28849) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47906437 macOS/iOS: macOS Apple Silicon
rpc : invalidate cached compute graph when a referenced buffer is freed (#24292) The server caches the most recent compute graph per device so that GRAPH_RECOMPUTE can re-execute it without resending
spacemit : fix wrong transpose function for int16 data (#25161) The sizeof(int16_t) branch in permute_transpose_impl calls rvv_transposed_s32_mn_to_nm instead of rvv_transposed_s16_mn_to_nm. This is a
CUDA/HIP: improve access patterns in im2col (#28013) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47937267 macOS/iOS: macOS Apple Silicon (arm64) macOS A
model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625) model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle ov
hexagon: accept the zeroed rope probe in supports_op (#28995) llama probes weight placement with a rope where all params are 0, so rejecting n_dims == 0 or freq_base == 0 puts rope_freqs on the CPU. T
hexagon: Support for K-Quants Q4_K and Q6_K (#28994) implement q6k/q4k kernels Squashed from: feat: implement q6k kernel hex-q6k: improve unpack accuracy hex-q4_k: add support for Q4_K kernels Co-auth
Enable CUDA graph for MTP draft (#28549) Improve CUDA graph usage for MTP Rename field Address review feedback Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestatio
TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965) model: calculate split states for attn_qkv from n_head * n_embd_head_k required for gemma4 with --fuse-qkv, where n_embd is 53
Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star