Search: “reasoning”

arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-au

arXiv:2610.11373v1 Announce Type: cross Abstract: Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading exist

arXiv:2610.11215v1 Announce Type: new Abstract: Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden b

arXiv:2610.11402v1 Announce Type: new Abstract: GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making p

arXiv:2610.05671v2 Announce Type: replace Abstract: Automatic prompt optimization (APO) has been widely employed to adapt large language models without updating their weights, yielding promising resul

arXiv:2610.10962v1 Announce Type: cross Abstract: Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied ta

Live results, coding benchmarks included, agentic benchmarks included, domains and other classifications filters included. (Spoiler: DeepSeek-V4-Vision-Exp rules, but other models have their rule area

arXiv:2610.10854v1 Announce Type: new Abstract: Knowledge distillation is an established technique for improving the capabilities of small, efficient student models by training them with the represent

arXiv:2610.11031v1 Announce Type: cross Abstract: A long-standing hypothesis in artificial intelligence and neuroscience posits that intelligence is closely related to compression: the ability to comp

arXiv:2610.12235v1 Announce Type: new Abstract: AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet thei

arXiv:2610.11316v1 Announce Type: cross Abstract: System One models output constrained decisions and probability distributions rather than free-form text generation. While prevailing paradigms rely on

arXiv:2610.11989v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision. However, uniform weighting overlooks

arXiv:2610.11442v1 Announce Type: new Abstract: Human mobility generation, an important task in urban research, synthesizes trajectory data for urban planning and transportation management. Human mobi

arXiv:2610.11526v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer an energy-efficient computing paradigm through sparse event-driven computation, showing great potential for effic

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Be

arXiv:2606.17924v2 Announce Type: replace-cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding

arXiv:2610.11382v1 Announce Type: cross Abstract: World models in end-to-end autonomous driving predict future scene evolution to provide foresight for trajectory planning. Existing methods mainly stu

arXiv:2610.11857v1 Announce Type: new Abstract: 3D scene inpainting aims to recover missing or occluded regions in edited 3D scenes, while ensuring geometric and textural consistency. Existing approac

arXiv:2610.10978v1 Announce Type: cross Abstract: When a field that an authority contract needs exists only in unstructured evidence, a model can sense it. We admit the model's output only as an obser

(Don't judge by the screenshot, the cache is cold. It hits 24+ tok/s with a warm cache!) About two months ago, I made a post here asking whether predicting which MoE experts would be used on the next

arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through

arXiv:2610.11058v1 Announce Type: new Abstract: In autonomous driving, understanding scene topology - the connectivity between lanes and traffic elements - is critical for safe path planning and motio

arXiv:2610.11451v1 Announce Type: new Abstract: We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows.

arXiv:2610.11766v1 Announce Type: cross Abstract: Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR). Yet the same non-harmful outcom

arXiv:2603.09163v2 Announce Type: replace Abstract: Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Naviga

arXiv:2610.11456v1 Announce Type: new Abstract: Two-photon calcium imaging is a standard tool for recording large neural populations in vivo, yet inferring spikes accurately across the growing diversi

All anyone ever talks in this sub is about x new model having x benchmark scores and how well it can code. Or some new tech to increase t/s for qwen. So I wanted to go back to the roots of this sub an

arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic ben

A bit of backstory : i got lucky in August and was able to grab a CMP 170 HX 8GB for around 500 on alibaba. I tried later to get a second one for around 1k but my order got cancelled and prices went t

arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use,

I tested Mellum2.1-12B-A2.5B (Q8) locally using Pi and llama-server. All five tests were one-shot. Results were pretty mixed: - Pelican SVG, Browser OS, Minecraft: Poor results. - Bouncing Hexagon: Ph

arXiv:2610.11504v1 Announce Type: new Abstract: Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These

TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Instead o

Release: ttok 1.0 I released ttok 0.4, ran uv tool upgrade ttok, piped a file into the new version... and realized that it was defaulting to the GPT-4 tokenizer when it should very clearly default to

arXiv:2610.12114v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student par

arXiv:2610.12281v1 Announce Type: cross Abstract: Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation

arXiv:2610.12161v1 Announce Type: cross Abstract: Why does removing reference-policy KL regularization sometimes improve group policy optimization? This motivates studying how reference-policy informa

arXiv:2610.11750v1 Announce Type: new Abstract: Tree-based speculative decoding verifies multiple draft continuations in one target-model pass, but finite trees built from draft scores face a fundamen

arXiv:2610.10805v1 Announce Type: new Abstract: As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developi

arXiv:2610.11247v1 Announce Type: cross Abstract: On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully u

arXiv:2610.10447v1 Announce Type: new Abstract: Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful traject

arXiv:2509.19571v2 Announce Type: replace-cross Abstract: Designing or learning robot policies that generalize zero-shot across a range of language instructions and objects is a core problem in roboti

arXiv:2610.09661v1 Announce Type: new Abstract: Automatic Short Answer Scoring (ASAS) is central to NLP for Education. However, openly available benchmarks remain scarce, and existing datasets largely

arXiv:2610.09446v1 Announce Type: new Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not de

arXiv:2610.09337v1 Announce Type: cross Abstract: Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; however, they are sample-inefficient

arXiv:2610.09026v1 Announce Type: cross Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavior