Capability Scaling-Down Laws for LLM Compression
arXiv:2610.02462v1 Announce Type: cross Abstract: LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable
Knowledge catalogue
arXiv:2610.02462v1 Announce Type: cross Abstract: LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable
arXiv:2610.02914v1 Announce Type: new Abstract: Autoregressive video models can generate minute-long videos in real time, but they produce generic subjects from text rather than specific subjects from
arXiv:2610.02375v1 Announce Type: cross Abstract: Dento-maxillofacial cone-beam CT (CBCT) reports may contain dozens of tooth-specific, anatomical, and spatial findings from a single 3D scan. Learning
arXiv:2610.02828v1 Announce Type: new Abstract: Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL re
arXiv:2610.02841v1 Announce Type: new Abstract: LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains und
arXiv:2610.03321v1 Announce Type: cross Abstract: Low-rank approximation can require additional matrix--vector products to verify that its error meets a prescribed tolerance. We characterize this cert
arXiv:2602.00066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constrai
arXiv:2610.02586v1 Announce Type: new Abstract: A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carrie
arXiv:2610.02359v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-qual
arXiv:2511.06260v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although
arXiv:2610.03367v1 Announce Type: new Abstract: We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incompara
arXiv:2610.02632v1 Announce Type: new Abstract: As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintai
arXiv:2610.03326v1 Announce Type: new Abstract: Diffusion language model (dLLM) compression faces a known challenge because calibration is typically performed on clean, fully visible activations, wher
arXiv:2610.02361v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are l
arXiv:2610.03436v1 Announce Type: cross Abstract: Speech-driven 3D facial animation can reproduce recognizable mouth poses. However, it can simplify the motion between them, and that motion carries co
arXiv:2610.02779v1 Announce Type: new Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video gener
arXiv:2610.02713v1 Announce Type: new Abstract: Most KV-cache compression methods classify attention heads once, either offline or during prefill, and keep this classification fixed throughout generat
Automated lint: 19 errors, 64915 warnings, 3 info
I forked llama.cpp's server into AgrillaMoE, a dedicated build for Qwen3.6-35B-A3B (~A4B) with Unsloth quants. On a (vant.ai) rented V100 16GB with the 2-bit UD-Q2_K_XL quant it generates at ~57-60 to
ggml-openvino: update to 2026.4.1, optimize performance, expand ops, improve device listing. (#29852) ggml-openvino : Qwen3.5 MoE perf (#312) Squash of ravi9#312: ggml-openvino: add detailed inference
ollama pull clef open models for all. start building with @ollama and @cloudflare clef decision models today .@Cloudflare's decision models are available on Ollama! Decision models allow you to classi
arXiv:2610.01253v1 Announce Type: new Abstract: Quantum Reinforcement Learning (QRL) integrates reinforcement learning with parameterized quantum circuits and is a promising approach to combinatorial
arXiv:2610.00568v1 Announce Type: cross Abstract: Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between cap
arXiv:2610.00049v1 Announce Type: new Abstract: Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardwa
arXiv:2610.01750v1 Announce Type: new Abstract: Cooperative 3D tracking must integrate complementary observations across agents and time while maintaining consistent identities. When evidence integrat
arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of
arXiv:2610.00422v1 Announce Type: cross Abstract: Neural combinatorial optimization typically assumes a centralized solver that reads the whole instance. We study the opposite: combinatorial optimizat
arXiv:2610.01494v1 Announce Type: new Abstract: Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature space
arXiv:2610.00094v1 Announce Type: cross Abstract: Belief-based agent memory needs reliable decisions about current state, yet its evidence may be noisy, copied, or stale. Must a memory calibrate its s
arXiv:2610.01069v1 Announce Type: new Abstract: Differentiable logic gate networks, which operate using only logic gates, have recently attracted attention as an efficient alternative to conventional
arXiv:2610.00483v1 Announce Type: new Abstract: Representation alignment (REPA) accelerates diffusion transformer training, but its alignment targets are almost exclusively semantic encoders such as D
arXiv:2610.00204v1 Announce Type: new Abstract: Visual-token compression for vision--language models is posed almost entirely as a selection problem: decide which tokens to keep and discard the rest.
arXiv:2610.00558v1 Announce Type: new Abstract: While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive
arXiv:2610.01206v1 Announce Type: new Abstract: Partially transmissive screens and protective covers are common in robotic inspection, but they create mixed LiDAR returns from both the foreground mate
arXiv:2610.01249v1 Announce Type: new Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffect
arXiv:2610.01973v1 Announce Type: new Abstract: Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: some
arXiv:2610.02162v1 Announce Type: new Abstract: How can a world model continuously observe regions beyond the actor's current view? Video world models simulate how an environment evolves from an agent
arXiv:2609.38762v1 Announce Type: cross Abstract: Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewri
arXiv:2609.39687v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student
arXiv:2609.39467v1 Announce Type: new Abstract: Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-wor
arXiv:2511.06947v2 Announce Type: replace-cross Abstract: The well-aligned attribute of CLIP-based models enables its effective application like CLIPscore as a widely adopted image quality assessment
arXiv:2609.40143v1 Announce Type: new Abstract: Compact regulatory DNA can free up space in vector payloads, reduce synthesis and assay burden, and expose which sequence features drive predicted activ
arXiv:2609.38748v1 Announce Type: new Abstract: Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization. However, applications such as AR/V
arXiv:2609.38562v1 Announce Type: new Abstract: World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations. Autoregress
arXiv:2609.39915v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents
arXiv:2609.38587v1 Announce Type: new Abstract: Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG founda
arXiv:2609.38360v1 Announce Type: cross Abstract: On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its
arXiv:2609.39685v1 Announce Type: cross Abstract: Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstration
arXiv:2609.38840v1 Announce Type: cross Abstract: Single-cell RNA-seq representation learning is fundamentally label-free: cell identities, states, and contexts are not fixed training targets, so what
arXiv:2607.10891v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interf
arXiv:2609.38287v1 Announce Type: cross Abstract: Simulation-augmented generation (SAGE) is a recent technical proposal in which models simulate individuals' viewpoints at inference time in order to p
arXiv:2609.38716v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value ca
arXiv:2609.38909v1 Announce Type: cross Abstract: Large language models often know the truth and say otherwise: a model that answers correctly when asked neutrally will affirm a user's mistaken belief
arXiv:2609.39496v1 Announce Type: cross Abstract: Typed decision models such as Jev offer an efficient alternative to generative LLMs in decision-making workflows by selecting directly from predefined
arXiv:2609.38816v1 Announce Type: new Abstract: While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems re
Our agent workflow is currently executing a group of 10 vllm api calls within a asyncio.gather we made them share the same prompt until the end where the queries/instruction prompts differ. These call
arXiv:2609.36495v1 Announce Type: new Abstract: Forward kinetostatics of spatial tendon-driven continuum robots typically requires a nonlinear equilibrium solve for each actuation input. This paper de
arXiv:2609.36241v1 Announce Type: new Abstract: Dexterous robotic hands typically reproduce human hand morphology but inherit its one-sided grasping workspace, requiring wrist or arm reorientation to
arXiv:2609.37829v1 Announce Type: new Abstract: Video diffusion transformers (DiTs) increasingly adopt mixture-of-experts (MoE) architectures to reduce active computation, but their full expert storag