Knowledge catalogue
arXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout
arXiv:2610.06902v1 Announce Type: new Abstract: Retrieval-augmented generation grounds language models in external context, but for long documents flat top-k retrieval can cluster on a single region a
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2610.06861v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the dominant paradigm for eliciting multi-step reasoning in large language models, an
arXiv:2610.06522v1 Announce Type: cross Abstract: A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. Using SycoLens, a modu
arXiv:2610.04490v1 Announce Type: new Abstract: As large language models (LLMs) grow in parameter count, model storage and parameter memory traffic have become major bottlenecks to efficient deploymen
arXiv:2610.05541v1 Announce Type: new Abstract: Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing tools primarily focus on the acti
arXiv:2610.05318v1 Announce Type: new Abstract: Analog in-memory computing is a promising platform for on-device execution of large language models because it performs matrix--vector multiplications (
arXiv:2610.03799v1 Announce Type: new Abstract: Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discret
arXiv:2610.02800v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple tokens for parallel verification. However, e
arXiv:2509.20810v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual er
arXiv:2610.02910v1 Announce Type: new Abstract: Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which e
arXiv:2607.14197v2 Announce Type: replace Abstract: Artificial Intelligence (AI) answer engines now field a growing share of the questions that analysts, scholars, and the public ask about issues of p
arXiv:2606.13176v2 Announce Type: replace Abstract: Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical fo
arXiv:2602.10273v3 Announce Type: replace-cross Abstract: Reasoning ability in large language models is often attributed to distribution sharpening: concentrating output probability on high-likelihood
arXiv:2610.03567v1 Announce Type: new Abstract: We describe the Writerslogic team's participation in the CLEF 2026 SimpleText shared task, addressing Task 1 (text simplification) and Task 2 (complexit
I've been looking at the <32B model space and keep coming back to an interesting question. A few years ago, projects like Hummingbird+ suggested that cheap custom accelerators (FPGA-based) might becom
So Kimi K2 is outdated, and so is GPT OSS 120b. Which of the modern open weights models can boast the least sycophancy? I need this both for creative/research assistant usage (sycophancy led me down b
arXiv:2610.01535v1 Announce Type: cross Abstract: Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparato
arXiv:2610.01230v1 Announce Type: new Abstract: Efficient long-context inference is essential for large language models (LLMs), yet it poses a severe computational bottleneck. Hash-based retrieval off
arXiv:2606.22826v2 Announce Type: replace Abstract: Evaluating LLMs across many model variants---quantized, fine-tuned, or deployment-specific---requires running large benchmarks repeatedly, a process
arXiv:2610.00809v1 Announce Type: new Abstract: Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one fra
arXiv:2606.13607v3 Announce Type: replace Abstract: When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not
arXiv:2610.00313v1 Announce Type: new Abstract: Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to
arXiv:2610.02023v1 Announce Type: new Abstract: While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making
arXiv:2610.00253v1 Announce Type: cross Abstract: Audits of AI visibility summarise the brand recommendations of deployed language models into per-system profiles. We test whether such a profile descr
arXiv:2610.00332v1 Announce Type: cross Abstract: Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current a
arXiv:2610.02190v1 Announce Type: new Abstract: Step-size selection remains a central challenge in large-scale neural network optimization; conservative steps slow convergence, while aggressive steps
arXiv:2610.00372v1 Announce Type: new Abstract: Large language model agents rely on external harnesses to pass information between the model and its environment and to recover from execution errors. Y
arXiv:2609.39279v1 Announce Type: cross Abstract: Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs).
arXiv:2609.38831v1 Announce Type: new Abstract: Model-attribution classifiers can often identify which language model produced a text, making model-specific writing patterns a signal of provenance. Ac
arXiv:2609.40148v1 Announce Type: new Abstract: Power-law learning curves are often treated as fixed properties of a model and its data, although learning-rate and batch-size schedules can change the
arXiv:2609.40286v1 Announce Type: cross Abstract: Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requested answer language can reopen seem
arXiv:2603.06350v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constrain
arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. Thi
arXiv:2609.38161v1 Announce Type: new Abstract: Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We
arXiv:2609.37853v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as social agents, yet credible human-like interaction requires more than fluent responses or pers
arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion,
arXiv:2609.35970v1 Announce Type: cross Abstract: Large language models are able to solve tasks whose answers depend on not only individual input tokens, but also on relations among them. How is such
arXiv:2609.36689v1 Announce Type: cross Abstract: Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that
arXiv:2609.35868v1 Announce Type: new Abstract: Is human readability necessary for effective fine-tuning of large language models? We investigate whether model-conditioned training representations can
arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture. H
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guid
arXiv:2609.35813v1 Announce Type: cross Abstract: Compact surrogates could reduce the cost of simulating large language model societies, but must reproduce collective behavior. We compare individual p
arXiv:2609.36692v1 Announce Type: cross Abstract: Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram represent
arXiv:2609.37915v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) trains a student to match a privileged teacher distribution along its own sampled trajectory. Standard OPSD applies
arXiv:2609.37577v1 Announce Type: new Abstract: Large Language Model judges are widely used to rank texts and text-generating systems through pairwise comparison, and their reliability is typically as
arXiv:2609.36159v1 Announce Type: new Abstract: Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between
arXiv:2609.37470v1 Announce Type: new Abstract: A probability used for a decision should refer to the same event across equivalent requests. We introduce probability contracts, a benchmark connecting
arXiv:2609.37493v1 Announce Type: cross Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error
arXiv:2609.37626v1 Announce Type: cross Abstract: No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tensor parallelism, many independen
arXiv:2609.36829v1 Announce Type: new Abstract: An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability wh
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since addi
arXiv:2609.38043v1 Announce Type: new Abstract: Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated us
Apple Foundation Model 3 through Private Cloud Compute is directly available in macOS 27.2 through familiar AI clients. For Mac users running local models such as Qwen 3.x or Gemma 4, AFM 3 PCC is a c
arXiv:2609.36535v1 Announce Type: new Abstract: Self-evolution lets large language models (LLMs) improve iteratively using their own generated data, but often suffers from self-evolution degeneration:
arXiv:2609.36830v1 Announce Type: new Abstract: Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation wit
I wanted a fun way to visualize and stress-test a multi-agent ecosystem, so I pointed it at my favorite MMO (a vanilla-era private server emulator). Live view: https://design.kristiantalley.com/projec
arXiv:2609.33192v1 Announce Type: new Abstract: Scientific code generation can produce executable programs that fail to compute the intended scientific object. We study this problem in language-model
arXiv:2609.35505v1 Announce Type: new Abstract: We study on-policy distillation (OPD) through the lens of reinforcement learning, establishing a connection between the reverse-KL objective in OPD and