Knowledge catalogue
Like many of you I've spent the last few days throwing Qwen3.8-27B against all of my usual use-cases and personal tasks/harnesses and workflows. It's great, phenomenal sometimes, but that's not what t
arXiv:2608.19197v1 Announce Type: cross Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environ
arXiv:2608.18105v1 Announce Type: cross Abstract: StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured quer
arXiv:2608.18144v1 Announce Type: cross Abstract: Modal auxiliaries such as must, should, and have to mark necessity and obligation within the contexts of speaker authority and interpersonal stance. W
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by another AI application or model, has become a standard,
arXiv:2608.18940v1 Announce Type: cross Abstract: Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by
arXiv:2601.17178v3 Announce Type: replace-cross Abstract: Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, s
arXiv:2608.18607v1 Announce Type: new Abstract: Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combi
arXiv:2608.18521v1 Announce Type: new Abstract: Dense-caption retrieval has recently been improved by introducing segmentation, edge maps, LLM-filtered captions, and cross-modal modules into contrasti
arXiv:2608.17534v1 Announce Type: new Abstract: Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains cont
arXiv:2608.17571v1 Announce Type: cross Abstract: Motivation: Low-dimensional embeddings are widely used to explore cell-state heterogeneity in single-cell and other high-dimensional biological data.
arXiv:2608.17620v1 Announce Type: new Abstract: Machine learning models for electroencephalography (EEG) analysis show great promise across a wide range of applications, but their deployment in high-r
(my own experience) I have a mid-range gaming laptop from 2024 with 4GB VRAM and 16GB RAM. There is nothing that I can run other than small models at humble t/s. I mostly use the models to generate sc
arXiv:2608.17370v1 Announce Type: new Abstract: Generative models promise a route to explainable clinical AI: rather than probe a classifier, model the distributions of healthy and diseased patients a
arXiv:2608.17164v1 Announce Type: new Abstract: Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by
arXiv:2608.15619v1 Announce Type: new Abstract: Emotion recognition from text keeps improving on benchmarks, yet whether an accuracy ceiling has been reached is seldom asked with discipline. Our aim i
arXiv:2608.16829v1 Announce Type: cross Abstract: Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual
arXiv:2608.15046v1 Announce Type: new Abstract: A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original. That quantity is least informat
arXiv:2603.13377v2 Announce Type: replace Abstract: Representation learning has driven major advances in natural image analysis by enabling models to acquire high-level semantic features. In microscop
In the DeepSWE benchmark a two‑stage approach of running DeepSeek V4 Pro 0813 first and falling back to GPT‑5.6 Sol when the tests fail achieves 83 % success at an average cost of 3.35 per task, compa
arXiv:2608.14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified.
I was checking out benchmarks of this model and apparantly better than Qwen3.5 9b reasoning across the bench on artificial analysis. I have used the 9b model for variety of stuff and it has been amazi
arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long
arXiv:2608.14552v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence
arXiv:2608.16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners. However, when
arXiv:2608.16637v1 Announce Type: new Abstract: LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead transla
arXiv:2602.12381v2 Announce Type: replace Abstract: Recent generative models produce near-photorealistic images, challenging the trustworthiness of photographs. Synthetic image detection (SID) methods
arXiv:2603.00801v2 Announce Type: replace Abstract: Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources
arXiv:2608.16643v1 Announce Type: cross Abstract: Automated detection of errors in clinical documentation is a promising application of large language models (LLMs), yet decisions to deploy such model
arXiv:2608.16765v1 Announce Type: cross Abstract: Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task
arXiv:2608.15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliab
arXiv:2608.16045v1 Announce Type: cross Abstract: LLM-based data-analysis tools are increasingly used to help users analyze messy spreadsheets and workbooks, from answering questions over uploaded fil
arXiv:2608.16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trus
arXiv:2608.16147v1 Announce Type: new Abstract: Class-imbalance handling is routinely evaluated on a single benchmark dataset, and the resulting conclusions are reported as if they were properties of
arXiv:2608.13573v1 Announce Type: new Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving syst
arXiv:2608.13900v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from conversational assistants into autonomous systems that execute long-horizon tasks through reasonin
arXiv:2608.14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may prop
arXiv:2608.13940v1 Announce Type: new Abstract: AI research agents (AIRA) can now propose, implement, and evaluate their own machine learning experiments, but progress on frontier tasks is throttled b
arXiv:2608.13854v1 Announce Type: new Abstract: Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular l
arXiv:2608.13766v1 Announce Type: new Abstract: Vision-language models (VLMs) remain unreliable on chart questions that require reasoning over visual quantities, and this weakness is usually attribute
arXiv:2608.13990v1 Announce Type: new Abstract: Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capt
arXiv:2603.21114v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) perform strongly on isolated spatial tasks, but whether their predictions remain persistent and mutually co
arXiv:2607.15740v2 Announce Type: replace-cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important
DeepSeek V4 Pro 0813 and Claude Fable 5 were benchmarked on DeepSWE. A cascading strategy that starts with Pro 0813 and escalates to Fable only when it fails solves 82.7 % of tasks at an average cost
arXiv:2608.13786v1 Announce Type: cross Abstract: Large language model (LLM) chatbots are increasingly used to answer clinical questions with citations to relevant clinical studies. Prior research has
arXiv:2608.13742v1 Announce Type: cross Abstract: In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifi
arXiv:2608.01856v2 Announce Type: replace Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-even
arXiv:2608.13608v1 Announce Type: new Abstract: Agentic 'Continual Learning Harnesses', systems that pair an LLM with retrieval or memory to improve from feedback without retraining, have shown growin
arXiv:2608.14106v1 Announce Type: cross Abstract: When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking
arXiv:2608.13922v1 Announce Type: new Abstract: Detecting distributional changes in high dimension is difficult when neither the pre-change nor post-change density is parametrically specified. We intr
arXiv:2608.13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe
arXiv:2608.13624v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, ra
arXiv:2608.14015v1 Announce Type: cross Abstract: Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a pr
arXiv:2608.14054v1 Announce Type: new Abstract: Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time
arXiv:2602.12498v2 Announce Type: replace Abstract: Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative f
arXiv:2608.14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on per
arXiv:2608.13797v1 Announce Type: new Abstract: Computational approaches to drug discovery involve multiple sub-problems, and among them, drug-target binding affinity prediction plays an important rol
arXiv:2506.01793v2 Announce Type: replace Abstract: Most current evaluations of foundation models focus on objective benchmarks, such as knowledge coverage and reasoning accuracy, often overlooking us
arXiv:2608.14104v1 Announce Type: cross Abstract: The Shapes Constraint Language (SHACL) is a W3C recommendation to express syntactic constraints, called shapes, on RDF graphs. SHACL validators are us
arXiv:2608.13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate reasoning is confined to the Thought phase: while th