DAPD: Dual-Anchored Policy Distillation
arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged informatio
Knowledge catalogue
arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged informatio
arXiv:2608.12980v1 Announce Type: new Abstract: Referring remote sensing image segmentation (RRSIS) aims to delineate targets specified by natural language expressions in remote sensing imagery. Exist
arXiv:2608.13316v1 Announce Type: cross Abstract: Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high infe
arXiv:2608.13010v1 Announce Type: new Abstract: Retrieval-augmented generation treats an external corpus as inference evidence, allowing injected documents to promote attacker-chosen claims. Existing
arXiv:2511.17007v2 Announce Type: replace-cross Abstract: Open and intelligent radio access networks (RANs) envisioned for 6G require accurate and reusable wireless channel knowledge for intelligent i
arXiv:2608.12574v1 Announce Type: new Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection fr
common : auto-detect spec type from draft GGUF metadata (#26814) common : auto-detect spec type from draft GGUF metadata When -md loads a local draft model without --spec-type, the sidecar inference i
arXiv:2608.12203v1 Announce Type: new Abstract: Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos, but ar
arXiv:2608.11361v1 Announce Type: cross Abstract: Tokenizer vocabulary size is a foundational design choice in large language model (LLM) infrastructure, yet it is typically fixed at training time bas
arXiv:2606.13840v2 Announce Type: replace-cross Abstract: Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and
On Aug 13 2026, OpenAI announced a preview of its “Ultrafast” mode for the GPT‑5.6 model, called Sol, which claims inference speeds up to 14× faster than current releases. The feature is initially rol
arXiv:2507.15958v5 Announce Type: replace-cross Abstract: On-device skin lesion analysis is constrained by the compute and energy cost of conventional CNN inference and by the need for lightweight cal
arXiv:2608.11704v1 Announce Type: cross Abstract: Dynamic Time Warping (DTW)-based Nearest-Neighbor (NN) classifiers are effective for time-series classification but are vulnerable to mislabeled train
arXiv:2608.11657v1 Announce Type: cross Abstract: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into
arXiv:2608.11403v1 Announce Type: new Abstract: Self-consistency (SC) via majority vote is a widely used way to spend inference-time compute: sample N chains of thought, return the plurality answer. O
arXiv:2608.10939v1 Announce Type: cross Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet
arXiv:2608.10235v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is abs
arXiv:2608.10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its pro
arXiv:2608.10232v1 Announce Type: cross Abstract: Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on
arXiv:2608.10860v1 Announce Type: cross Abstract: World-action models (WAMs) predict the future to act better, but nearly all of them predict only RGB latents, trained purely for pixel reconstruction,
arXiv:2608.10843v1 Announce Type: new Abstract: First-order concept synthesis asks a system to infer one formula that classifies labeled objects consistently across several finite relational structure
LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both
arXiv:2608.10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured
arXiv:2608.10483v1 Announce Type: new Abstract: Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because avai
arXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-acce
arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data
arXiv:2608.10810v1 Announce Type: cross Abstract: Emotion understanding in discourse requires reasoning beyond surface sentiment because speakers often convey affect through indirect, implicit, polite
arXiv:2608.10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures
arXiv:2608.10928v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. Howev
arXiv:2608.10903v1 Announce Type: new Abstract: Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in
We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B
arXiv:2604.04902v2 Announce Type: replace Abstract: Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models)
arXiv:2608.09638v1 Announce Type: new Abstract: Theory of Mind (ToM) is essential for agent interactions, yet existing evaluations either rely on static scenarios that oversimplify mental-state reason
arXiv:2608.08621v1 Announce Type: new Abstract: Running a business is a challenging form of intelligent work. Operators must infer opportunities from partial signals, commit capital under uncertainty,
arXiv:2506.02791v4 Announce Type: replace-cross Abstract: In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread
arXiv:2608.08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the i
arXiv:2509.16609v2 Announce Type: replace Abstract: Accurately assessing image complexity (IC) is essential for many vision tasks, yet existing approaches rely almost exclusively on visual features an
arXiv:2603.19329v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations
arXiv:2604.02047v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward p
arXiv:2608.09484v1 Announce Type: new Abstract: Many diffusion-based planners enforce safety through inference-time guidance, but such interleaved trajectory deformations often degrade kinematic feasi
arXiv:2507.01900v3 Announce Type: replace Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional
I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes. I froze DeepSeek V4 Flash and a 417M-parameter Moon
arXiv:2608.08588v1 Announce Type: cross Abstract: Hamiltonian Monte Carlo (HMC) is a successful generic inference method in probabilistic programming, but in its ordinary formulation it needs gradient
arXiv:2511.20849v2 Announce Type: replace-cross Abstract: We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed
arXiv:2608.07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to st
arXiv:2608.08721v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically dete
arXiv:2602.23290v2 Announce Type: replace Abstract: Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompo
NVIDIA Nemotron 3.5 Lightning is an open‑source mixture‑of‑experts language model totaling 30 B parameters with only 3 B active during inference, designed to serve high‑volume, low‑latency execution f
arXiv:2608.08600v1 Announce Type: cross Abstract: World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environment
arXiv:2608.08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging. Existing met
arXiv:2505.15062v5 Announce Type: replace-cross Abstract: Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly availab
arXiv:2508.04224v2 Announce Type: replace Abstract: Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appe
arXiv:2608.08528v1 Announce Type: new Abstract: Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries,
💡The world needs an open-source platform, and that’s exactly what we’re building to give our customers more choice and the flexibility to choose the right model for the right task. As part of this, we
arXiv:2608.07193v1 Announce Type: cross Abstract: Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fix
arXiv:2608.06849v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression
arXiv:2608.07183v1 Announce Type: new Abstract: Multimodal fusion architectures typically assume all modalities are available at inference, yet sensor failures, acquisition variability, and cost const
arXiv:2608.06878v1 Announce Type: new Abstract: Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrat
arXiv:2608.06839v1 Announce Type: new Abstract: Artificial Neural networks (ANNs) are often treated as black-box models, making explainability a central challenge in deep learning. Many engineering me