Knowledge catalogue
arXiv:2609.18317v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from a long-tail deficit: culturally specific facts, particularly those concerning underrepresented regions such a
arXiv:2609.18720v1 Announce Type: new Abstract: Learned quality estimation (QE) models such as COMETKiwi are widespread and work well for general machine translation evaluation. However, they are know
arXiv:2609.17602v1 Announce Type: new Abstract: Computational text-based ideal point estimation (CT-IPE) methods are usually compared as named algorithms, yet applying them involves numerous researche
arXiv:2609.18007v1 Announce Type: cross Abstract: Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether
arXiv:2609.18440v1 Announce Type: new Abstract: Lindsey et al. (2025) report that Claude 3.5 Haiku plans rhymes: features for candidate rhyme words are active on the newline before a line is written,
I was testing this quantization IQ3_XXS from GSQ-RCO with PI. It is a heavy quantization case, the model is in IQ3_XXS and KV cache in (Q4_0, Q4_0). I asked it to make the flight simulator, using that
arXiv:2609.18249v1 Announce Type: new Abstract: Real-world recommendation scenarios are commonly grounded in shared physical environments during user-recommender interactions. This motivates situated
arXiv:2609.18134v1 Announce Type: cross Abstract: Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work
arXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We in
arXiv:2609.18128v1 Announce Type: new Abstract: Large language model (LLM) agents augmented by tools can automate complex, multi-step tasks, such as web navigation, code generation, and workflow orche
arXiv:2609.18194v1 Announce Type: new Abstract: In Taiwanese Hokkien automatic speech recognition (ASR), prior studies often treat tone sandhi as a major challenge under the assumption that models fai
arXiv:2609.17997v1 Announce Type: cross Abstract: Selective state space models (SSMs) have recently emerged as a compelling alternative to transformers, combining competitive performance with substant
arXiv:2609.18163v1 Announce Type: new Abstract: Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept se
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
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
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: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:2609.16962v1 Announce Type: new Abstract: Open-vocabulary multimodal emotion recognition (OV-MER) aims to generate open natural-language emotion labels from multimodal affective cues. In real-wo
arXiv:2609.16679v1 Announce Type: new Abstract: Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems mod
arXiv:2609.16036v1 Announce Type: cross Abstract: We developed DAMM-Net++, a 2.5D architecture for thoracic OAR and target volume segmentation that addresses three persistent challenges in radiotherap
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
Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back to shipped code. That's where much of the industry's serious engineering runs now.
can you draw a picture of a flower in gimp? So I ran through this setup to install the MCP server suite from GITHUB, it's pretty easy to follow the install - and installs the libraries necessary to co
arXiv:2609.16755v1 Announce Type: new Abstract: Brain tumor segmentation remains difficult because enhancing tumor (ET) has low contrast and overlaps surrounding tissue, while scanner and site variati
arXiv:2609.17043v1 Announce Type: cross Abstract: Multi-hop question answering requires combining information from multiple documents to answer complex questions. These systems have grown increasingly
arXiv:2609.16907v1 Announce Type: cross Abstract: AI companions can provide meaningful relationships, yet these relationships remain vulnerable to platform-initiated changes. We study AI companion dis
arXiv:2609.17247v1 Announce Type: new Abstract: An agentic AI driver-assistance framework that integrates perception, compliance reasoning, vehicle-state interpretation, and safety arbitration into a
arXiv:2609.17226v1 Announce Type: cross Abstract: An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the repor
arXiv:2609.16635v1 Announce Type: new Abstract: Computer-use agents increasingly operate browsers, software, and desktop applications via CLI or API portals, but graphical user interface (GUI) still p
arXiv:2609.15990v1 Announce Type: new Abstract: Few-shot prompting sometimes degrades language models instead of helping them, but why this happens is unknown. We evaluate 12 open-weight models on two
arXiv:2509.09710v3 Announce Type: replace-cross Abstract: This study introduces a Large Language Model (LLM) scheme for generating key attributes of travel diaries in agent-based transportation models
arXiv:2609.17099v1 Announce Type: new Abstract: Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconst
arXiv:2609.17306v1 Announce Type: cross Abstract: Multi-agent Systems (MAS) combine multiple model outputs to solve complex reasoning tasks. However, despite rapid growth of available open-source mode
arXiv:2609.16873v1 Announce Type: new Abstract: Pediatric brain tumors are a leading cause of cancer-related mortality in children, and their small, rare, and often low-contrast subregions make accura
Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, that stored answer goes stale. Adobe researchers write each
arXiv:2609.16129v1 Announce Type: new Abstract: A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to
arXiv:2609.17251v1 Announce Type: new Abstract: We introduce a simple architectural modification to decoder-only transformers: a persistent recurrent state that observes hidden representations via cro
arXiv:2505.13388v4 Announce Type: replace-cross Abstract: Reward models are essential for aligning language model outputs with human preferences, yet existing approaches often lack both controllabilit
arXiv:2609.16427v1 Announce Type: new Abstract: This paper presents a Belarusian-specific data-cleaning pipeline and fine-tuning for English-Belarusian machine translation. Our cleaning pipeline disti
Rene has a really neat multiplayer agentic experience. I run several agents at once. So I lose track of important conversations throughout the day. Rene pulls conversations from my inbox and manages t
arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions re
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o
I am planning to buy hardware to run local models. I'm not sure what kind of hardware is best and what will I be able to run. I'm torn between getting a used M1 Max 64gb Macbook for €1500, M3 Max 128g
arXiv:2609.16340v1 Announce Type: new Abstract: Machine translation systems are periodically upgraded to stronger models, but the available preference signal is human post-edits of an older system's o
arXiv:2609.17422v1 Announce Type: new Abstract: Audio-driven digital human generation plays an important role in virtual communication, immersive interaction, and media production. With the developmen
arXiv:2609.16229v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modif
The essay below from Aaronson is just unmoored from reality, sorry. It is just not true, if you try to approach the question in a data-oriented fashion, rather than via vibes and speculative fiction a
arXiv:2609.16073v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) serves as the primary memory architecture for long-horizon autonomous agents. However, treating shared memory as
arXiv:2609.16927v1 Announce Type: cross Abstract: Subliminal learning is a phenomenon in which a distillation dataset transmits traits from the teacher model that are not legibly encoded in the datase
arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates con
arXiv:2609.16537v1 Announce Type: cross Abstract: Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the analytical kno
arXiv:2609.15980v1 Announce Type: cross Abstract: When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the
arXiv:2609.14413v1 Announce Type: cross Abstract: Large language model (LLM)-based database migration is often treated as direct code transformation, although enterprise Oracle systems contain heterog
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pre
arXiv:2609.14592v1 Announce Type: new Abstract: Artificial intelligence systems are rapidly becoming critical components in healthcare, finance, public services, and other safety-critical domains. Yet
arXiv:2609.13612v1 Announce Type: new Abstract: Modern AI systems are built on the Transformer architecture, whose core operation, attention, accounts for the majority of computation and memory cost.
OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv
arXiv:2609.13264v1 Announce Type: cross Abstract: Generating human-centric videos that preserve both visual identity and person-specific expressive behavior remains a fundamental challenge. In additio
arXiv:2609.14467v1 Announce Type: cross Abstract: Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR
arXiv:2609.15478v1 Announce Type: new Abstract: Multimodal agents can create complex videos in software such as Blender by coding without relying on diffusion models. Yet video understanding benchmark