Knowledge catalogue
arXiv:2601.19956v2 Announce Type: replace-cross Abstract: As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emer
arXiv:2609.03254v1 Announce Type: new Abstract: Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here i
arXiv:2609.03515v1 Announce Type: new Abstract: Decoding-time KV cache compression research focuses heavily on designing better token scoring functions, while the temporal rule that aggregates scores
arXiv:2609.03681v1 Announce Type: new Abstract: Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and poten
arXiv:2603.26236v2 Announce Type: replace Abstract: While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process c
arXiv:2609.02616v1 Announce Type: new Abstract: Emotion-driven image editing aims to evoke a specified target emotion by modifying emotion-relevant visual cues in a source image, while preserving the
Ling-3.0-flash-Fin is the first finance-enhanced model in the Ant Ling family. Developed by Ant Group with leading financial institutions and domain experts, it extends Ling 3.0 flash through continue
arXiv:2609.01834v1 Announce Type: new Abstract: As enterprise platforms transition to conversational reasoning interfaces, the stateless nature of LLM APIs creates an architectural gap. While stateles
arXiv:2609.02414v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mech
arXiv:2601.07468v2 Announce Type: replace Abstract: Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization
arXiv:2609.02502v1 Announce Type: cross Abstract: Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce vis
arXiv:2609.02131v1 Announce Type: cross Abstract: Sentiment in social-media threads does not only vary across posts; it shifts as users react to claims, corrections, evidence, and hostility within a b
arXiv:2609.01833v1 Announce Type: new Abstract: Sentence-level recognition of depression symptoms is challenging because similar expressions can differ in symptom relevance, and language-model inferen
arXiv:2609.02265v1 Announce Type: new Abstract: Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information c
arXiv:2510.07177v2 Announce Type: replace Abstract: Aspect-based summarization has attracted significant attention for its ability to generate more fine-grained and user-aligned summaries. While most
arXiv:2609.01673v1 Announce Type: cross Abstract: Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve t
arXiv:2609.02620v1 Announce Type: new Abstract: Generative AI is changing how cultural artifacts are created and circulated, and with it our understanding of creativity itself. Researchers disagree ab
arXiv:2609.02730v1 Announce Type: new Abstract: Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user beh
arXiv:2609.02270v1 Announce Type: cross Abstract: Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing
arXiv:2609.02496v1 Announce Type: new Abstract: Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). Howe
I've tried both and been having this debate with myself for the last few days, on two Asus Ascent GX10s (effectively the same as 2x DGX Spark): DeepSeek-V4-Flash-0731 (official weights) GLM-5.3-Flash
arXiv:2602.02028v3 Announce Type: replace Abstract: Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a c
arXiv:2609.02677v1 Announce Type: cross Abstract: Modern portfolio management increasingly demands a balance between traditional risk-adjusted returns and strict Environmental, Social, and Governance
arXiv:2609.02679v1 Announce Type: cross Abstract: When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited huma
arXiv:2609.02168v1 Announce Type: new Abstract: Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through th
arXiv:2609.02683v1 Announce Type: new Abstract: Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramid
arXiv:2609.02106v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly explore many candidate states of relational data in parallel, each of which should remain isolated, rep
arXiv:2603.03718v2 Announce Type: replace Abstract: Glass surface segmentation from RGB images is a challenging task, with a number of applications in robotics and scene understanding. As glass lacks
arXiv:2609.01918v1 Announce Type: new Abstract: Energy poverty is nearly absent from NLP-for-social-good, and the little existing work is either static retrieval/QA or relies on carbon-intensive cloud
arXiv:2609.01736v1 Announce Type: cross Abstract: Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, exist
arXiv:2609.01617v1 Announce Type: cross Abstract: Getting accurate, grounded answers out of large enterprise document repositories is a difficult problem. Dense vector retrieval alone frequently perfo
arXiv:2609.01839v1 Announce Type: cross Abstract: Longitudinal prediction from electronic health records (EHRs) is limited by the sparsity and irregularity in patient trajectories, and knowledge augme
It started as a fork of llama-swap, but I have been building it out for myself since then as a convenient tool for all my local AI needs, and by now it has drifted far enough to be its own thing. The
arXiv:2609.02805v1 Announce Type: new Abstract: Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing performance degradations in modern 5G and emerging 6G network
arXiv:2609.02548v1 Announce Type: cross Abstract: Modern large language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilit
arXiv:2609.02649v1 Announce Type: new Abstract: Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industri
arXiv:2603.21653v2 Announce Type: replace Abstract: Predicting the next mobile app a user will launch is essential for proactive mobile services. Yet accurate prediction remains challenging in real-wo
arXiv:2505.21907v3 Announce Type: replace Abstract: AI copilots represent a new generation of AI-powered systems designed to assist users, particularly knowledge workers and developers, in complex, co
arXiv:2505.00759v3 Announce Type: replace-cross Abstract: The steady improvements of text-to-image (T2I) generative models lead to slow deprecation of automatic evaluation benchmarks that rely on stat
arXiv:2609.01657v1 Announce Type: cross Abstract: Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision enco
arXiv:2609.01896v1 Announce Type: cross Abstract: Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while p
arXiv:2609.02606v1 Announce Type: new Abstract: Loneliness is a critical public health issue among older adults, linked to higher risks of depression, cognitive decline, and mortality. Scalable, objec
arXiv:2609.02549v1 Announce Type: cross Abstract: Drug-target interaction (DTI) prediction is an important task in AI-driven drug discovery. Although recent biochemical representation learning methods
A potato can create a very cool RPG in 24 minutes Laptop I3 8gb RAM 0gb VRAM, Windows 11 llama-server.exe --host 0.0.0.0 --port 8080 -m modelsqwen3.6-35b-InstructQwen_Qwen3.6-35B-A3B-IQ2_XXS.gguf -c 8
ik_llama.cpp merged qwen4exp MTP support yesterday (PR #2369, mine, reviewed and tested by four other people on their own hardware). It's on main now, no fork or patch needed. Posting since the last c
arXiv:2609.01811v1 Announce Type: cross Abstract: No single optimization method is uniformly best for all problems, and the most suitable optimizer choice can change during a run. Existing approaches
arXiv:2609.02749v1 Announce Type: new Abstract: Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for plannin
arXiv:2609.02497v1 Announce Type: cross Abstract: Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-d
arXiv:2609.02731v1 Announce Type: cross Abstract: Large vision-language models have achieved remarkable success in vision-language tasks. However, they remain prone to Visual Hallucinations (VHs), und
arXiv:2609.02292v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: sele
arXiv:2511.20279v3 Announce Type: replace Abstract: End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single,
arXiv:2602.05605v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) are costly at high resolution because self-attention scales quadratically with token sequence length. Existing p
arXiv:2609.01936v1 Announce Type: cross Abstract: A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states int
arXiv:2609.01810v1 Announce Type: new Abstract: Farsi, spoken by more than 120 million people, lacks a comprehensive benchmark for dialogue generation and understanding. We introduce TALKFA, a unified
arXiv:2609.02244v1 Announce Type: new Abstract: Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete. Task-level natural-language priors can provide
arXiv:2609.02115v1 Announce Type: cross Abstract: Natural language interfaces to databases have traditionally suffered from three structural limitations: exclusive targeting of relational SQL, uncondi
arXiv:2609.02049v1 Announce Type: cross Abstract: LLMs latent-state reasoning methods replace discrete intermediate tokens with continuous states, such as weighted mixtures of token embeddings, to ret
arXiv:2507.08468v2 Announce Type: replace Abstract: This paper provides an experimental evaluation of the capability of large language models (LLMs) to assist in legal decision-making within the frame
arXiv:2609.01621v1 Announce Type: cross Abstract: Artificial intelligence (AI) increasingly treats scientific literature as a data source for building databases, training predictive models, and guidin
arXiv:2609.02083v1 Announce Type: cross Abstract: Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, a