Search: “reasoning”

arXiv:2604.01142v2 Announce Type: replace-cross Abstract: Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test condi

arXiv:2610.05129v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not a

arXiv:2610.04836v1 Announce Type: new Abstract: Remote sensing agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quant

arXiv:2610.06605v1 Announce Type: new Abstract: Transformers asked to multiply multi-digit numbers in a single forward pass often fail, and interpretability studies of pretrained language models find

arXiv:2610.06804v1 Announce Type: new Abstract: A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the inco

arXiv:2610.06383v1 Announce Type: new Abstract: Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space

arXiv:2602.02180v2 Announce Type: replace Abstract: Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexit

Zeyi Yang / New York Times: Study: China is struggling to attract foreign AI talent; for every 30 Chinese AI researchers in the US in 2025, only one in China made the opposite journey — China's boomin

Surprising AI life hack for email management that will save you from inbox overwhelm. You can give your AI agent its own email address (Instinct does this automatically) and use that email address for

arXiv:2407.21783v3 Announce Type: cross Abstract: Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It i

arXiv:2610.05885v1 Announce Type: new Abstract: Many works approach continual learning through the lens of infinite context windows. As an agent puts more observation into context (concretely the KV c

arXiv:2610.06494v1 Announce Type: new Abstract: Multi-structure segmentation of the uterus is important for computer-assisted screening, diagnosis, and treatment planning of uterine diseases, where ul

Someone who has always loved looking at the space between different AI techniques, this time I went a little deeper into the memory trade-offs between RNNs, Transformers and SSMs. I found it interesti

arXiv:2603.23478v2 Announce Type: replace Abstract: Affordance segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interacti

arXiv:2610.04432v1 Announce Type: new Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manu

arXiv:2610.06672v1 Announce Type: new Abstract: Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended

arXiv:2610.05700v1 Announce Type: new Abstract: Recurrent sequence models must decide how strongly to overwrite their memory at each token. Read as Bayesian filtering, this write is the gain of a Kalm

arXiv:2610.05818v1 Announce Type: new Abstract: Vision-language-action models (VLAs) act on instructions without being able to refuse, so screening harmful requests falls to monitors. We test whether

arXiv:2610.05598v1 Announce Type: new Abstract: An organization often holds too little labeled data to train a model that generalizes, and the records that would supply the rest sit with organizations

arXiv:2610.03715v1 Announce Type: cross Abstract: We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as execut

arXiv:2610.03458v1 Announce Type: new Abstract: Post-training with verifiable rewards can induce reward hacking, motivating the use of monitors within the training objective rather than solely for off

arXiv:2610.02451v1 Announce Type: new Abstract: Effective wildfire monitoring requires relating visual evidence to physical fire dynamics, yet real videos with synchronized physical annotations are sc

arXiv:2610.02472v1 Announce Type: cross Abstract: Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (A

arXiv:2610.02438v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic kno

arXiv:2610.03141v1 Announce Type: new Abstract: Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that sup

arXiv:2610.02739v1 Announce Type: new Abstract: Agentic Text-to-SQL systems can interact with users to clarify underspecified queries before generating SQL. However, a correct execution result does no

arXiv:2610.02853v1 Announce Type: new Abstract: Safety heads are lightweight classifiers attached to pretrained language models for flagging harmful inputs before generation. Their empirical detection

arXiv:2610.02829v1 Announce Type: new Abstract: Large language models are increasingly used in clinical settings. However, research into the reliability and performance of these models has focused alm

Congrats to the Reflection team on Beam 🎉 Be sure to join us next week at our NYC meet-up with the Reflection team and NVIDIA https://luma.com/TAIxNvidiaxReflection Introducing Beam: a highly efficien

arXiv:2610.02972v1 Announce Type: new Abstract: Large language models (LLMs) can support rubric-based screening of CVs, but applying a high-capability model to every candidate and criterion is costly.

arXiv:2607.19060v2 Announce Type: replace-cross Abstract: Fast prediction of the response of adhesive soft viscoelastic contacts represents a current challenge in soft robotics and for gripping and ma

Does telling your agent to plan ahead actually help? It's standard practice to add a 'plan ahead' or 'think about the other players' instruction to an agent's prompt. In auctions and matching markets,

arXiv:2610.02744v1 Announce Type: new Abstract: Epidemic intervention policies are textual artefacts that human decision-makers interpret, justify, and revise through natural language, making large la

arXiv:2505.21870v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG coul

arXiv:2610.03374v1 Announce Type: new Abstract: Embodied world models enable scalable simulation of embodied interactions for robot learning. However, existing models are prone to Model Laziness, as t

Excited about the new open model from @reflection_ai! More US models coming to Ollama! Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier rea

arXiv:2610.03066v1 Announce Type: cross Abstract: GC--EI--MS is an important technique for analyzing volatile and semivolatile compounds in complex samples. However, conventional methods rely heavily

arXiv:2610.03522v1 Announce Type: new Abstract: Feed-forward novel view synthesis has recently shown promising results from sparse posed images, but most existing methods assume that context and targe

arXiv:2610.03361v1 Announce Type: cross Abstract: Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline

arXiv:2610.03389v1 Announce Type: new Abstract: Vision language models (VLMs) incur substantial inference cost because every visual token is processed by the attention and MLP projections of every dec

arXiv:2610.01511v2 Announce Type: replace Abstract: Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although aut

After some recommendations for hardware (I'm starting from nothing), in the region of £6-7k. I will be mainly looking to use it for coding and have found Deepseek V4.1 Flash or Qwen3.8 27b good and so

arXiv:2610.02858v1 Announce Type: new Abstract: Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback. When such an agent is di

arXiv:2610.02504v1 Announce Type: new Abstract: Balancing electricity demand and supply is increasingly difficult due to the inherent intermittency of renewable power generation and the stochastic pow

This is related to my previous post where I shared an encoder-only transformer model trained on ohiot1dm + shanghait1dm + azt1d datasets. This time I trained the model on the outputs of my T1DM patien

Blind A/B arena where AI agents build things in Blender and you vote on which result is better: https://render-arena.izolight.xyz Each agent gets a prompt that describes its environment and the rules,