Knowledge catalogue
At the core of AI, you really just need: 1) a thing that does 2) connections into tools 3) a place to hold stuff 4) a spot to share and update In slot 1, we're talking AI agents like Codex or Claude C
The August edition of my sponsors-only monthly newsletter is out. If you are a sponsor (or if you start a sponsorship now) you can access it here. This month: We got more details on OpenAl's accidenta
arXiv:2609.03478v1 Announce Type: new Abstract: We report on our ongoing project to develop a computational pipeline, AutoGraphForge, for an automated graph-theoretic conjecturing-refuting-formalizing
SYCL: Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45153754 macOS/iOS: macOS Apple Silicon (arm64
sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION. ADD+ADD uses the same binbcast indexing and type matrix as standalone
src : add n_expert_used_max function (#28323) src : add n_expert_used_max function With Commit c61b98b ('model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)') it is now poss
ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45199911
common : make build info output stream configurable (#28322) Let llama_print_build_info write to a caller-provided FILE* instead of hardcoding stderr. The parameter defaults to stderr so existing call
llama.cpp : bump version to 0.4.0 (#28386) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45314398 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
opencl: add Adreno xmem SDPA path (#26331) opencl: add Adreno xmem SDPA path Assisted-by: Codex Removed the Adreno-specific queue profiling override Clean up formatting 修复数值误差优化gqa/mask attn Assisted-
opencl: extend the elementwise and data‐movement op coverage (#27633) opencl: add extended elementwise unary ops (sgn, step, elu, hardswish, hardsigmoid, floor, ceil, round, trunc) Adds nine GGML_UNAR
metal : add remaining fa-vec tunings for M3 (#28396) addition of m3 in fa_vec_tuned_table adding q4_0,q4_1,q5_0,q5_1 in ggml-metal-tuning Fix formatting in ggml-metal-tuning.cpp Website: https://llama
Banger paper from Tencent on environment evolution. Environment supply is becoming the main limit on agent RL. So this is worth a read. (bookmark it) Agent RL needs a steady supply of environments har
arXiv:2609.03151v1 Announce Type: cross Abstract: Long-context reasoning for large language models (LLMs) is becoming increasingly important, but training over long sequences remains challenging due t
arXiv:2601.22931v2 Announce Type: replace Abstract: The prevalence of rapidly evolving slang, neologisms, and highly stylized expressions in informal user-generated text, particularly on Chinese socia
arXiv:2606.09655v2 Announce Type: replace Abstract: Despite remarkable progress in machine translation (MT), non-AI communities have raised growing concerns about MT systems, suggesting a noticeable g
arXiv:2609.03900v1 Announce Type: new Abstract: Continual knowledge-updating methods are often declared superior from one final checkpoint and one conventional adapter rank. We show that this can be i
arXiv:2609.03953v1 Announce Type: new Abstract: Understanding the frequency of factual errors in chatbot-generated text and evaluating systems that detect these errors is critical for determining chat
arXiv:2605.06508v2 Announce Type: replace-cross Abstract: Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. H
arXiv:2609.03887v1 Announce Type: new Abstract: How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three pos
arXiv:2609.03443v1 Announce Type: new Abstract: The performance of Flow Matching largely depends on the quality of the coupling between the source and target distributions. However, independent coupli
arXiv:2609.02895v1 Announce Type: new Abstract: Large-scale public events, such as religious festivals, political rallies, and cultural gatherings, are increasingly vulnerable to the rapid disseminati
arXiv:2609.03497v1 Announce Type: cross Abstract: Developing humanoid robots capable of leveraging human behavioral data is essential for general-purpose embodiment, yet conventional development remai
Brilliant new paper from the Qwen team. It provides insights into where agent training environments actually come from. Terminal agent trajectories have accumulated at scale while realistic executable
arXiv:2609.03502v1 Announce Type: cross Abstract: In low-resource settings, deploying TTS typically requires choosing between a large voice-cloning model with costly inference or a compact fixed-voice
arXiv:2609.03721v1 Announce Type: cross Abstract: Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented
arXiv:2604.17125v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) widens the prompt injection attack surface of large language model applications to tool descriptions, paramet
arXiv:2609.03407v1 Announce Type: new Abstract: People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory
Check out this week’s shipping recap: — Gemini 3.8 Flash, our most intelligent workhorse model yet, delivers upgrades across coding, agentic workflows, and critical multi-step reasoning. — Gemini 3.8
Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month,
arXiv:2609.03394v1 Announce Type: new Abstract: Emotion recognition benchmarks often predict one emotion per text, missing many real-world scenarios where two people arrive at opposing emotions from a
arXiv:2609.03901v1 Announce Type: cross Abstract: We present a comparative evaluation of six information retrieval methods for the task of academic advisor discovery: ranking CS faculty members by rel
arXiv:2609.02899v1 Announce Type: new Abstract: Benchmark contamination, the leakage of test items into training data, is widely described as a threat to the reliability of large language model (LLM)
arXiv:2609.03273v1 Announce Type: new Abstract: Tamil spell and grammar correction is challenging because Tamil is an agglutinative low-resource language with rich verbal morphology, complex sandhi (p
arXiv:2609.04070v1 Announce Type: new Abstract: Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physics-constrained nature of autonomous driving remains a
arXiv:2609.03977v1 Announce Type: cross Abstract: Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future intelligent
arXiv:2609.04083v1 Announce Type: cross Abstract: MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish scenes containing the same concepts but different
arXiv:2609.03221v1 Announce Type: new Abstract: Counterfactual audits are the standard tool for checking whether a clinical agent treats demographically distinct but clinically identical patients diff
arXiv:2609.03233v1 Announce Type: new Abstract: Camera traps have become an essential tool for wildlife monitoring, motivating the development of computer vision methods for the automated extraction o
arXiv:2609.03533v1 Announce Type: new Abstract: Existing theories derive neural scaling from data geometry or a specified data-model spectrum, but systems trained on the same data can scale differentl
arXiv:2609.03190v1 Announce Type: cross Abstract: Many biomedical challenges can be posed as tensor completion problems where the observed entries of a multidimensional array (a tensor) are used to im
arXiv:2609.03526v1 Announce Type: new Abstract: Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains unclear whether this success reflects genuine cult
arXiv:2509.17154v2 Announce Type: replace-cross Abstract: Hamiltonian dynamics describe a wide range of physical systems. As such, data-driven simulations of Hamiltonian systems are important for many
arXiv:2609.03064v1 Announce Type: cross Abstract: Federated learning allows banks, hospitals, and other regulated organizations to train a shared model without moving raw records off their own servers
arXiv:2602.10009v3 Announce Type: replace Abstract: Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary p
arXiv:2609.02898v1 Announce Type: new Abstract: Large domain-specific language models such as BioBERT and ClinicalBERT achieve strong performance on biomedical NLP tasks, but their computational deman
arXiv:2609.03438v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeas
arXiv:2609.03673v1 Announce Type: new Abstract: Video generators build long videos by composing shorter parts, either by generating segments one after another or by autoregressively extending chunks.
Hey everyone, been a while! https://huggingface.co/TheDrummer/Artemis-31B-v1.1 https://huggingface.co/TheDrummer/Artemis-31B-v1 A few months ago, Gemma graced us with models that served as a much need
arXiv:2512.22007v2 Announce Type: replace Abstract: DuaDeep-SeqAffinity is a sequence-only deep learning framework that predicts antibody--antigen binding affinity directly from primary amino acid seq
arXiv:2509.25175v3 Announce Type: replace-cross Abstract: Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted mani
arXiv:2609.03352v1 Announce Type: cross Abstract: Constant optimization refines the numerical coefficients of candidate expressions in tree-based genetic programming for symbolic regression. But its p
arXiv:2609.03654v1 Announce Type: cross Abstract: The comparative analysis of banks' financial statements poses significant challenges for automated question answering systems due to their complexity,
arXiv:2602.08216v3 Announce Type: replace Abstract: We derive two attention operators from generalized statistical entropies. Kaniadakis entropy yields an exact full-support normalization whose weight
arXiv:2609.04128v1 Announce Type: new Abstract: Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesiz
arXiv:2609.02982v1 Announce Type: new Abstract: Learning solution operators across broad parameter ranges can require substantial coverage of both input functions and physical parameters, particularly
arXiv:2609.03143v1 Announce Type: cross Abstract: We use tools from nonlinear algebra to study the equilibria of small linear translational spring networks. Specifically we use the techniques of homot
arXiv:2609.04197v1 Announce Type: cross Abstract: Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, producing prompts up to 3imes longer y
arXiv:2609.03814v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance on standard content moderation benchmarks. However, these benchmarks often aggregate multipl
arXiv:2510.17460v2 Announce Type: replace Abstract: Idioms remain a persistent challenge in natural language processing due to their figurative and culturally grounded meanings, which distinguish them