Knowledge catalogue
arXiv:2608.30372v1 Announce Type: new Abstract: As Large Language Models rapidly advance, performance on standard multiple-choice question answering (MCQA) benchmarks is reaching saturation. While the
arXiv:2608.28945v1 Announce Type: new Abstract: Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such
arXiv:2608.30751v1 Announce Type: new Abstract: Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether
arXiv:2608.30181v1 Announce Type: new Abstract: We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for agentic applicat
qwen4exp: sum the indexer heads by slices (#28023) qwen4exp: sum the indexer heads by slices The head reduction went through a transpose and a sum_rows over ne[1], which left sum_rows with ne0 = 4, on
qwen4exp: support recurrent state rollback (#28123) MTP speculative decoding needs the target state to move back by the number of rejected draft tokens. Without rollback support the context is classif
ci: Bump ggml-org/ccache-action to v1.2.24 (#28083) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44375174 macOS/iOS: macOS Apple Silicon (arm64) macOS Ap
metal: enable Metal 4.0 tensor API on M5+/A19+ (#27461) metal : request Metal 4.0 language version for the tensor API metal : load the tensor API kernels from a separate metallib tests : add external-
tests : fix log verbosity for test-llama-archs (#28147) tests : fix log verbosity for test-llama-archs cont : naming cont : add note Website: https://llama.app Attestations: https://github.com/ggml-or
qwen4exp: fix seq_cp, block position keying, mtmd input, cuda abort, add tests (#27941) qwen4exp: follow up fixes -kvu NaN collapse fix Assisted-by: Claude indexer cache ext.x/ext.y restore fix Assist
sycl : support limit max alloc memory within 2GB for host-pinned memory (#27559) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44438607 macOS/iOS: macOS A
metal : add fa-vec tuning for M2 Max (#28015) Rows for M2 Max (30 GPU cores) collected with 'ggml-metal-tuning fa-vec --dtype f16,q8_0', pasted into fa_vec_tuned_table. ref: https://github.com/ggml-or
metal : fix more leaks due to missing autoreleasepools (#27883) metal : fix more leaks due to missing autoreleasepools metal : rename variable metal : fix another missing pool warning Co-authored-by:
model : load hparams.n_layer_nextn before n_layer() calls (#28159) load hparams.n_layer_nextn before n_layer() calls remove duplicate loads Website: https://llama.app Attestations: https://github.com/
metal : add fa-vec tunings for A18 Pro (MacBook Neo) (#28152) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44474754 macOS/iOS: macOS Apple Silicon (arm64
metal : add fa-vec tuning for M2 Pro (#28122) metal: add fa-vec tuning for M2 Pro metal : update fa-vec tuning for M2 Pro with new dtypes Website: https://llama.app Attestations: https://github.com/gg
context : autoscale n_ctx_train when yarn scaling specified (#28030) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44499127 macOS/iOS: macOS Apple Silicon
kv-cells: look up the n-gram history in the sequence position index (#28040) get_prev_tokens() rebuilt a (seq, pos) -> token hash map on every ubatch by walking all used cells, while llama_kv_cells al
cuda: fuse MoE weighted expert reduction (#25952) cuda : fuse MoE weighted reduction (mul + view + add) The MoE combine tail currently writes weighted expert outputs to global memory before reducing t
arXiv:2608.30044v1 Announce Type: new Abstract: Language models are commonly compared by averaging scores across a benchmark list with equal weight. Such lists grow through publication outside an expl
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva
Banger paper from the Qwen team. If you evaluate agents on anything longer than a single session, this one is worth your time. (bookmark it) E-Commerce Bench runs an agent through a simulated 365-day
arXiv:2608.29196v1 Announce Type: new Abstract: Optic disc (OD) segmentation is essential for diagnosing ophthalmic pathologies from retinal fundus images. However, prevailing deep learning approaches
arXiv:2608.30536v1 Announce Type: new Abstract: Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of mu
arXiv:2608.29463v1 Announce Type: cross Abstract: A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status.
arXiv:2608.30418v1 Announce Type: cross Abstract: Resting-state functional magnetic resonance imaging (rs-fMRI) functional connectivity (FC) matrices are widely used for individual-level prediction, b
arXiv:2608.29127v1 Announce Type: new Abstract: We propose a scalable, validity-oriented pipeline for evaluating biomedical LLM judges when high-quality human judgments are scarce. First, we augment e
arXiv:2608.29990v1 Announce Type: cross Abstract: Large language models are increasingly deployed in Arabic-speaking markets, yet standard benchmarks overwhelmingly reward Modern Standard Arabic (MSA)
arXiv:2608.29804v1 Announce Type: new Abstract: Virtual try-on (VTON) requires not only realistic generation but also faithful preservation of garment characteristics. However, existing evaluation met
arXiv:2606.16206v2 Announce Type: replace Abstract: Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learnin
arXiv:2608.24621v2 Announce Type: replace Abstract: Can language models be trusted in safety- critical operations? In such settings, strong per- formance on semantic metrics does not guaran- tee opera
arXiv:2508.14323v3 Announce Type: replace Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none
arXiv:2608.28725v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final-
arXiv:2608.30686v1 Announce Type: cross Abstract: Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity can
arXiv:2608.28646v1 Announce Type: new Abstract: Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and dive
arXiv:2608.29928v1 Announce Type: new Abstract: State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechani
arXiv:2608.29345v1 Announce Type: new Abstract: While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user queries
arXiv:2510.01359v3 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, ra
arXiv:2608.30076v1 Announce Type: new Abstract: Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integr
NVIDIA and CrowdStrike evaluated an “agentic” cyber‑defense platform that fuses NVIDIA’s Nemotron open‑model family with Falcon telemetry for a continuous offense‑defense closed loop running at machin
arXiv:2607.10286v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs tha
arXiv:2608.30110v1 Announce Type: cross Abstract: Nowcasting headline macroeconomic indicators, i.e., estimating an indicator's value for the current reference period before its official release, is c
Information technology services company CBTS Technology Solutions LLC today launched Forge Agents, a platform that turns a plain-language description of a job into a working artificial intelligence ag
arXiv:2608.30427v1 Announce Type: new Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, preserv
arXiv:2608.29464v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness
arXiv:2608.29887v1 Announce Type: new Abstract: Multiple-choice question answering (MCQA) benchmarks in NLP use number-right scoring (accuracy), but in educational testing, the scoring scheme, the com
arXiv:2608.30762v1 Announce Type: new Abstract: Chess board recognition is the task of mapping the image of a chess board to the information of which piece is on which square. So far this task has two
Ben Patterson / PCWorld: Claude Fable 5.1 and Mythos 5.1 are Anthropic's first models to watermark text outputs; a detection API is available to eligible groups as required under EU law — Aside from b
Today is Claude Fable (and Mythos) 5.1 day. Anthropic say that Fable 5.1 'sets a new standard for coding, knowledge work, and long-running problem-solving tasks'. Their announcement spends a notable a
Claude Fable 5.1 tops the Artificial Analysis Intelligence Index but costs 20% more per task than Fable 5 despite a 75% cache read price cut We supported @AnthropicAI with pre-release evaluation of Cl
arXiv:2608.28784v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently made strong progress in visual--linguistic understanding. However, their performance on text-cent
arXiv:2608.29284v1 Announce Type: new Abstract: Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-re
I got the CMP170 cards and unlocked them. I wanted to share my set up for CUDA since maybe it would be useful to others. First off, I hate e-waste and we are in a special time for RAM. I wanted to hav
arXiv:2608.30337v1 Announce Type: new Abstract: Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than
arXiv:2608.30968v1 Announce Type: cross Abstract: We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artif
arXiv:2608.30109v1 Announce Type: new Abstract: Large Language Models (LLMs) trained on extensive scientific research are increasingly integrated as assistants for scientific discovery. However, most
arXiv:2608.30289v1 Announce Type: new Abstract: Vision-language-action (VLA) models remain brittle in manipulation tasks that require physical commonsense. Current physical VQA data is typically disem
CommerceAgentBench starts with real commercial demand, and Qwen3.8-Max delivers the strongest overall performance among open-weight models. Let's test Qwen on your real-world workflows! 🔥 Most AI benc
arXiv:2608.29934v1 Announce Type: new Abstract: KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may
arXiv:2608.30183v1 Announce Type: cross Abstract: Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) re