Search: “llm”

Recently I've flipped from being bullish to being bearish about AI. I think I'm updating my bearishness to be more solidly bearish. Early thoughts (which I hope to be disproven in the next year or so,

arXiv:2607.22572v1 Announce Type: new Abstract: Large language models can generate fluent SQL from natural language, but on real enterprise Oracle databases they frequently fail at execution time: col

arXiv:2607.22713v1 Announce Type: new Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historic

arXiv:2607.24300v1 Announce Type: new Abstract: Self-improving agents accumulate capability by repeatedly rewriting procedural policies, controllers, or heuristic rules. They typically rely on self-au

arXiv:2607.24492v1 Announce Type: new Abstract: The goal of schema integration is, given a set of input schemata or tables, to derive a global, unified schema that is able to represent the concepts, a

arXiv:2607.23976v1 Announce Type: cross Abstract: Appending a two-word confirmation tag to a decision question -- 'Is X the better choice?' versus 'X is the better choice, right?' -- changes whether a

The Kimi K3 architecture figure for yesterday's big open-weight model release, along with some observations and thoughts. 1. Yes, it looks relatively complicated, but it's essentially a scaled-up prod

arXiv:2607.22574v1 Announce Type: new Abstract: Evidence-based clinical decision making requires specialists to identify, evaluate and synthesize relevant scientific literature. However, PubMed search

arXiv:2607.23838v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query t

arXiv:2607.23854v1 Announce Type: new Abstract: Humans often find good solutions to combinatorial optimization problems that are computationally hard even for advanced computer algorithms. In the Eucl

arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe

arXiv:2607.22656v1 Announce Type: cross Abstract: Objective: This paper investigates the gendered structure of speaker addressee relationships in film dialogue, asking not merely who speaks, but who i

arXiv:2607.21632v1 Announce Type: new Abstract: Traditional benchmarks for LLMs primarily rely on static datasets and objective scoring metrics, which often fail to capture differences in response qua

arXiv:2607.21716v1 Announce Type: new Abstract: Due to the complexity of neural network loss landscapes, optimization theory is forced to rely on idealized models, and there is generally a tradeoff be

mtmd: Add Vision Support for Minimax-M3 (#25113) Add preliminary MiniMax-M3 support Text-only port that re-uses existing components: MiniMax-M2 style GQA with per-head QK-norm and partial rotary, Deep

I've been working on an open-source workflow automation platform over the past few months, with Ollama as one of the first-class providers rather than treating it as an afterthought. The goal wasn't t

arXiv:2607.22511v1 Announce Type: cross Abstract: Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approa

arXiv:2607.21861v1 Announce Type: new Abstract: We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book:

arXiv:2607.22136v1 Announce Type: new Abstract: Empathetic Response Generation (ERG) requires models to recognize users' emotions and generate empathetic responses. Commonsense knowledge has been show

arXiv:2607.10428v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: person

arXiv:2607.22444v1 Announce Type: new Abstract: For scale-invariant deep networks, Hyperball-style optimizers have shown strong performance in large-scale training by fixing the norms of matrix-valued

arXiv:2508.01782v4 Announce Type: replace-cross Abstract: Recently, large language models (LLMs) have driven promising progress in lossless image compression. However, directly adopting existing parad

arXiv:2508.05618v2 Announce Type: replace Abstract: Reasoning Large Language Models (R-LLMs) have significantly advanced complex reasoning tasks but often struggle with factuality, generating substant

arXiv:2607.21692v1 Announce Type: cross Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input. These selectors are often trained

Running local models means every token counts — an 8K or 16K window fills up fast when you're stuffing graph context into prompts for RAG. I benchmarked 10 graph serialization formats (JSON, GraphML,

There is a lot of buzz around running 100B parameter models on cheap local hardware using ternary (1.58-bit) quantization like Microsoft's BitNet architecture. The theoretical hardware shortcuts are i

I have been running some experiments with smaller open-weight LLMs on multiple-choice questions of Swedish medical licensing exams. On a dataset called MedQA-SWE, GPT-4 scored 84% accuracy in 2024 and

Large language models (LLMs) are transforming recommender systems from matching co-occurrence patterns in historical behavior toward reasoning about the intent that drives it. RecGPT-V1 pioneered this

Yes, open-source / open-weight models are important for a healthy AI ecosystem. That's how we can verify things, check claims, and keep up outside the closed labs. Plus, it gives us the freedom to run

Claude Opus 5 generated an entire game demo from Scratch, with no external assets used—Matt Shumer posted a video of the AI‑created gameplay on Twitter. The clip, narrated by Shumer as “AI games are g

arXiv:2607.21482v1 Announce Type: new Abstract: Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their

arXiv:2607.20498v1 Announce Type: new Abstract: Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-h

arXiv:2607.21424v1 Announce Type: new Abstract: Recent advancements in automated audio captioning (AAC) have shifted from monolithic sentence generation toward structured formats that explicitly disen

arXiv:2607.20439v1 Announce Type: new Abstract: Political evasion is difficult to detect because evasive answers often appear cooperative while avoiding concrete commitment. We present AsymVerify, a c

arXiv:2607.21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes

arXiv:2607.20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradit

arXiv:2607.20463v1 Announce Type: new Abstract: This paper presents an AI-driven browser extension that identifies clickbait to help users avoid misleading Internet articles. Moving beyond traditional

arXiv:2607.20526v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone i

arXiv:2607.20448v1 Announce Type: new Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license. Domyn-Small is the product of an i

arXiv:2508.16947v2 Announce Type: replace-cross Abstract: Despite significant progress, imitation learning-based autonomous driving planners remain largely restricted to reproducing high-frequency bia

arXiv:2607.21412v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially i

arXiv:2607.20485v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet

arXiv:2607.21042v1 Announce Type: new Abstract: Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deploy

arXiv:2607.20581v1 Announce Type: cross Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat

having an event stream like activegraph is the base of how we move to next level and that will probably be composition, which can let you achieve better results with smaller models. - get the core eve

arXiv:2607.21019v1 Announce Type: new Abstract: Traditional approaches to wearable health signal analysis, such as smartwatches, are constrained by rigid analytical frameworks and limited personalisat