Knowledge catalogue
ZeroDrift Inc., a startup that automates compliance for artificial intelligence communications, today launched Anchor 3.0, a family of small language models designed to check messages generated by AI
arXiv:2609.24510v1 Announce Type: new Abstract: Recent advances in vision foundation models (VFMs) have shown remarkable capabilities across diverse unimodal visual tasks. However, adapting VFMs to re
arXiv:2609.22212v1 Announce Type: new Abstract: Organizations in critical national infrastructure sectors must assess heterogeneous documents for sensitivity before routing or storage. Manual assessme
arXiv:2609.24328v1 Announce Type: new Abstract: Combining predictions from different models can improve performance at machine learning tasks, but the training of the individual models and the rule us
arXiv:2609.22836v1 Announce Type: new Abstract: Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse forecasting tasks. However, real-world dec
arXiv:2609.24384v1 Announce Type: new Abstract: Recognizing hand-drawn geometric shapes is a foundational sub-problem of sketch recognition, with applications in education, human-computer interaction,
arXiv:2609.22109v1 Announce Type: new Abstract: Selective on-policy distillation trains a student only at the token positions a selector scores highest, and the literature compares selectors under a s
arXiv:2609.23408v1 Announce Type: new Abstract: In frame interpolation tasks, motion ambiguity in the training set causes models to generate blurry intermediate frames. Moreover, the assumption of uni
arXiv:2609.24565v1 Announce Type: new Abstract: Architectural drawings encode material classes through repeated hatch patterns. We test whether a connectome-constrained fly visual network, pretrained
arXiv:2609.24124v1 Announce Type: new Abstract: Active perception and manipulation are crucial for robots to interact with complex scenes. Existing benchmarks struggle to evaluate how robots effective
arXiv:2609.22562v1 Announce Type: new Abstract: Multi-vector visual document retrieval (VDR) models such as ColPali and ColNomic achieve strong accuracy by representing each document with hundreds to
arXiv:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follo
arXiv:2609.22185v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a mesh-free approach for solving differential equations, but their performance can depend strongly on l
arXiv:2609.23084v1 Announce Type: new Abstract: Over-the-air federated learning lets edge devices transmit their local updates simultaneously, reducing the communication overhead. The resulting wavefo
arXiv:2609.24058v1 Announce Type: new Abstract: Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages and the difficulty of serving dive
arXiv:2609.22323v1 Announce Type: new Abstract: Few-shot learning research is predominantly evaluated on accuracy alone, with limited attention to the parameter and training-sample budgets required to
arXiv:2609.22114v1 Announce Type: new Abstract: Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression pre
arXiv:2609.22973v1 Announce Type: new Abstract: Adapting a pretrained Vision-Language-Action (VLA) model to a new robot, environment, or task requires demonstrations that are collected locally and oft
arXiv:2602.04068v2 Announce Type: replace Abstract: The calculation of shortest-path distances in road networks is a core operation in navigation systems, location-based services, and spatial analytic
arXiv:2609.22917v1 Announce Type: new Abstract: Non-technical stakeholders frequently cannot write the SQL needed to extract insights from operational databases. We built and evaluated a Text-to-SQL a
arXiv:2609.24170v1 Announce Type: new Abstract: Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency,
arXiv:2609.24312v1 Announce Type: new Abstract: Analog video transmission (VTX) remains widespread in FPV drones due to low latency, weight and low cost. However analog VTX suffers from complex spatia
arXiv:2609.24737v1 Announce Type: new Abstract: We introduce Ananke, a representation-learning framework that scaffolds latent representations onto a structured product-torus prior, and its flagship v
arXiv:2609.23345v1 Announce Type: new Abstract: As generative AI becomes increasingly used in anime-style image creation, distinguishing human-drawn, AI-inpainted, and text-to-image images is importan
Anthropic says its new Claude Opus 5.5 model comes with stronger safeguards in the wake of recent rogue AI hacking incidents. In an announcement on Tuesday, Anthropic says Opus 5.5 comes with improvem
David Gewirtz / ZDNET: Anthropic raises its five-hour usage limits by 20% on Pro, Max, and Team plans, and gives subscription users a rate limit reset — Anthropic's newest Claude model aims to make fr
Despite rampant worries about runaway artificial intelligence, the two big AI model makers aren’t yet slowing down: Anthropic PBC released Claude Opus 5.5 today and cut its price 20%, and minutes late
Matthias Bastian / The Decoder: Anthropic says Opus 5.5 matches Fable 5.1 “on most tasks” while costing about 40% less to run than Opus 5; Opus 5.5 costs 4/1M input and 20/1M output tokens — Ask about
Anthropic's Claude Opus 5.5 is now available in Hermes Agent via Nous Portal! OPUS 5.5 BENCHMARKS JUST DROPPED. It beats Fable 5.1 and GPT 6 Astra across the board. Agentic coding, knowledge work, rea
arXiv:2609.23976v1 Announce Type: new Abstract: Robots engaged in fast physical interactions often need to act before the intent of another agent is fully known. Anticipatory goalkeeping illustrates t
arXiv:2609.22455v1 Announce Type: new Abstract: We present Apollo Restore, a 24-billion-parameter large language model for restoring lacunae---physical gaps---in fragmentary Ancient Greek texts. Fine-
arXiv:2609.23133v1 Announce Type: new Abstract: Recent advances in vision-language-action models have stimulated growing interest in underwater embodied intelligence. However, their reliance on large-
arXiv:2609.23578v1 Announce Type: new Abstract: As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action
arXiv:2609.22803v1 Announce Type: new Abstract: Simulations for learning-based autonomous colonoscopic navigation focus mainly on fully actuated capsule robots, failing to capture the contact-rich nav
arXiv:2609.22894v1 Announce Type: cross Abstract: Coreset selection picks a representative subset of the labeled training set to make training cheaper. However, it is usually evaluated by downstream a
arXiv:2609.24401v1 Announce Type: new Abstract: Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constrai
As part of our efforts to pace the frontier, we’re committed to supporting independent assessments with deep levels of access across training, evaluation, and deployment. That access should enable thi
arXiv:2609.24099v1 Announce Type: new Abstract: Body-cue recognition can support assistive robots, but benchmark accuracy does not guarantee reliable behavior under a robot-camera viewpoint. We presen
arXiv:2609.23146v1 Announce Type: new Abstract: Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inven
arXiv:2504.11582v3 Announce Type: replace Abstract: How can a monolingual English speaker determine whether an automatic translation in French is good enough to be shared? Existing MT error detection
arXiv:2609.24650v1 Announce Type: new Abstract: Readability assessment is essential for tailoring texts to intended audiences across educational, healthcare, and information retrieval domains. However
At Box, we've been testing Opus 5.5 on a variety of complex enterprise knowledge work tasks dealing with unstructured data with the Box Agent. Overall, we saw frontier capability levels, with major pe
arXiv:2609.23039v1 Announce Type: new Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their b
arXiv:2609.22584v1 Announce Type: new Abstract: As industrial processes grow in complexity, traditional Proportional-Integral-Derivative (PID) controllers are often insufficient for handling their non
arXiv:2609.22302v1 Announce Type: new Abstract: Medical vision-language models can propose how urgently a skin lesion should be reviewed, but the local service retains authority to accept or replace t
arXiv:2609.22913v1 Announce Type: new Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live sy
metal : fix mask bounds in flash attention block pre-pass (#29220) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49087452 macOS/iOS: macOS Apple Silicon (
vendor : update cpp-httplib to 0.57.1 (#29239) Signed-off-by: Adrien Gallouët adrien@gallouet.fr Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49092442 ma
hexagon: new HMX-optimized GATED_DELTA_NET (#29199) hex-gdn: start putting together HMX support for GDN hex-gdn: working hmx but not-pipelined and slow for now hex-gdn: re-write vtcm layout handling a
opencl: add A8 Q4_0 non-MoE dp4a binary kernel (#29055) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49141307 macOS/iOS: macOS Apple Silicon (arm64) macO
ci : publish snapdragon builds in release workflow (#29007) The snapdragon CI builds packages only to feed the QDC device tests, so Hexagon NPU binaries never reached the releases page. Build both tar
chat : Fix Muse Glimmer tool-call first parser error (#29242) Fix Muse Glimmer tool-call first parser error Add test to verify Condense patterns remove test for trigger patterns Website: https://llama
cmake : allow repeated find_package calls for llama (#29228) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49213556 macOS/iOS: macOS Apple Silicon (arm64)
convert: add MiMo-V2.6 support (#29257) convert: add MiMo-V2.6 support Hoist the K3 mxfp4 conversion repack into base.py so it can be reused Remove decoder from mmproj convert Update conversion/mimo.p
spec : support DFlash for HunyuanOCR (#28890) model : add DFlash layer-input taps for HunyuanVL DFlash speculative decoding needs the target graph to expose the residual stream entering each layer (re
server: Add support for binding to multiple addresses (#28690) Add support for binding llama-server to multiple addresses Assisted-by: Codex remove redundant thread handler make it clear about overlap
jinja: use const for statement::execute and ::visit (#29271) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49279983 macOS/iOS: macOS Apple Silicon (arm64)
ggml : IQ1_M build prefix sums once per block (#28706) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49294443 macOS/iOS: macOS Apple Silicon (arm64) macOS
metal : gate mul_mm_id src1 rescale behind ggml_prec (#29029) metal : gate mul_mm_id src1 rescale behind ggml_prec Assisted-by: Claude Fable 5.1 ggml-webgpu: reject MUL_MAT_ID when src1 precision is F
mtmd: add various sanity checks (#29276) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49308522 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon