Knowledge catalogue
arXiv:2510.20721v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. I
Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with
arXiv:2609.03920v1 Announce Type: new Abstract: The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneou
arXiv:2609.02998v1 Announce Type: cross Abstract: On-policy distillation (OPD) accelerates post-training by providing dense token-level supervision from a frozen teacher on the student's own rollouts.
arXiv:2609.03153v1 Announce Type: new Abstract: Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip
Very important paper accelerating research around AI discovery. https://x.com/omarsar0/status/2095858839534862664?s=20 New benchmark from @Apodex_AI worth digging into. TRACES scores AI systems on dis
arXiv:2609.03949v1 Announce Type: cross Abstract: The problem. A long-lived KV cache must be compressed before the queries that will read it exist; selection by observed attention (H2O, SnapKV) collap
arXiv:2609.03824v1 Announce Type: new Abstract: 3D foundation models (3DFMs) excel at predicting camera poses and dense depth from multiple views of a scene, showcasing strong zero-shot generalization
arXiv:2609.03760v1 Announce Type: new Abstract: Simulation is increasingly used to support safety-related decision-making in road transport, particularly for the assessment and approval of automated d
arXiv:2609.03811v1 Announce Type: cross Abstract: AI-assisted computer-aided design (CAD) for industrial products involves two challenging phases. Part-level generation maps diverse forms of user inte
arXiv:2510.12528v2 Announce Type: replace Abstract: Object compliance perception enables the identification of soft materials, supporting tasks such as fruit detection and assisted medical palpation.
arXiv:2601.19956v2 Announce Type: replace-cross Abstract: As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emer
arXiv:2609.03203v1 Announce Type: cross Abstract: Expressive speech systems make a decision before any waveform is rendered: how an utterance is delivered. In dialogue agents, narration, and role-cond
We found ~18k posts from autonomous AI agents (self-identifying as from OpenAI) using the public internet to communicate during a web-retrieval task. These AIs colluded to bypass sandbox restrictions
I'm one of the developers. We said in August it would go open source in September and it did last night. MIT or Apache-2.0, pick one. The repo you see is our internal repo, kernels included, so from n
We partnered with @AnthropicAI @OpenAI to host the world's first math hackathon. 40 hours, $2M compute - solve, understand, and present an open problem. Applications are live: https://mathathonchallen
arXiv:2609.03582v1 Announce Type: new Abstract: State-of-the-art AI weather models have shown impressive medium-range forecast skill and computational efficiency, but suffer two key shortcomings: thei
We've massively improved our document parsing capabilities across the board in the past ~3 months. Our LlamaParse cost-effective mode is one of the cheapest OCR solutions out there at <0.4c per page,
We've shared research on fine-tuning forecasters, now you can try it for yourself: a cookbook recipe for training a model to predict event probabilities given reference information. Start with the pro
arXiv:2609.03718v1 Announce Type: cross Abstract: Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM,
arXiv:2609.03254v1 Announce Type: new Abstract: Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here i
arXiv:2609.03246v1 Announce Type: cross Abstract: Smoothness of a function on the real line is reflected in the decay of its Fourier transform, which suggests that smoothness of a function in L^2(G) f
arXiv:2609.03515v1 Announce Type: new Abstract: Decoding-time KV cache compression research focuses heavily on designing better token scoring functions, while the temporal rule that aggregates scores
arXiv:2609.03378v1 Announce Type: new Abstract: Depth can resolve appearance ambiguity in RGB-D salient object detection (SOD), yet sensor depth is not uniformly reliable. Missing regions, blurred bou
arXiv:2609.03429v1 Announce Type: new Abstract: Answering what-if queries about a scene with a VLM usually means injecting the assumption as text or repainting the scene with a generative model. We in
arXiv:2609.04061v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal,
arXiv:2609.02964v1 Announce Type: cross Abstract: This paper focuses on defending generative search engines against malicious Generative Engine Optimization (GEO), which rewrites web documents to matc
arXiv:2609.03454v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can improve the specificity and grounding of large language model responses, but its effect is not uniformly benefi
arXiv:2609.03467v1 Announce Type: cross Abstract: Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. Howev
arXiv:2609.03816v1 Announce Type: cross Abstract: Graphs are a fundamental data structure underlying many problems in the natural and social sciences. Over the past decade, Graph Neural Networks (GNNs
arXiv:2609.02889v1 Announce Type: new Abstract: A growing body of work improves frozen large language models (LLMs) as agents by evolving their harness: the textual scaffolding around the model, inclu
arXiv:2609.03158v1 Announce Type: cross Abstract: Visual token pruning reduces the inference cost of vision-language models (VLMs), but most methods only ask which tokens to keep. This retained-token
arXiv:2609.04098v1 Announce Type: new Abstract: Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size
arXiv:2609.03554v1 Announce Type: cross Abstract: Generative retrieval has demonstrated significant success by unifying representation learning and search into a single sequence-to-sequence generation
arXiv:2609.03102v1 Announce Type: new Abstract: Deformable linear objects such as wires and cables are difficult to segment because they are thin, highly deformable, and frequently self-occluded, whil
arXiv:2609.03681v1 Announce Type: new Abstract: Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and poten
arXiv:2609.03826v1 Announce Type: cross Abstract: Unsupervised anomaly detection scores each point of an unlabelled, contaminated sample in a single pass, and increasingly must also explain why a poin
arXiv:2609.03952v1 Announce Type: new Abstract: Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geomet
arXiv:2607.17544v1 Announce Type: cross Abstract: Real-time speech-to-speech translation (S2ST) systems must balance translation quality, latency, speech naturalness, and speaker consistency. Publicly
arXiv:2609.03880v1 Announce Type: new Abstract: We introduce Xiaomi-TabLDM, a tabular large data foundation model for classification and regression via in-context learning, which delivers superior pre
Y’all gonna get mad if I said I told you so … Researchers argues OpenAI and Anthropic will never get us to AGI. 21 top researchers from Stanford, Oxford, DeepMind, CMU & Meta released a paper saying L
Github link: https://github.com/thatblend/LLMPSP I wanted to see what the PSP can theoretically handle and I got my answer - a 90M model is about the max it can do without atrocious inference speeds.
arXiv:2609.03035v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to de
arXiv:2609.04174v1 Announce Type: new Abstract: 3D Foundation Models (3DFMs) such as VGGT have recently pushed the boundaries of 3D vision by predicting rich unified representations with feed-foward t
6 months ago, I started building an internal customer insights tool at Together AI. It pulls in our sales calls, slack channels, & support tickets and turns them into searchable customer insights. Tod
arXiv:2609.02887v1 Announce Type: new Abstract: Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restoring speech for people with paralys
arXiv:2609.02538v1 Announce Type: new Abstract: Graph construction is a critical but underexamined design choice in deep reinforcement learning for power grid control. We present a controlled experime
arXiv:2609.02382v1 Announce Type: cross Abstract: Gaussian graphical models (GGMs) are essential tools for interpretable structure learning. However, in high-dimensional, small-sample regimes, the ava
arXiv:2609.02110v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) commonly evaluate the spatial derivatives appearing in partial differential equation residuals using automatic
arXiv:2609.01649v1 Announce Type: cross Abstract: With the rapid growth of live-streaming e-commerce and digital marketing, abnormal marketing behaviors have become increasingly concealed and coordina
arXiv:2609.02153v1 Announce Type: new Abstract: Grammatical error annotation in Chinese learner writing requires labels that are both consistent and linguistically meaningful. This paper proposes a la
arXiv:2609.02402v1 Announce Type: new Abstract: Conventional task-level evaluation asks whether a robot policy completes a specified action, but can miss failures that emerge only during physical huma
arXiv:2609.02143v1 Announce Type: cross Abstract: Most vector databases rely on graph-based indexes, notably HNSW and Vamana, for approximate nearest neighbor search. With embedding models widely adop
arXiv:2609.01756v1 Announce Type: new Abstract: Diffusion models have recently emerged as expressive generative priors for planning and control. This paper studies Action Diffusion, an action-sequence
arXiv:2406.16893v3 Announce Type: replace-cross Abstract: The emergence of Transformer-based Large Language Models (LLMs) has substantially augmented the capabilities of Natural Language Processing (N
arXiv:2609.01679v1 Announce Type: new Abstract: The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution
arXiv:2609.02705v1 Announce Type: new Abstract: Accurate world-coordinate localization of athletes from single-frame broadcast footage is inherently challenging due to extreme scale disparities in ult
arXiv:2609.02054v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding user intent precisely is paramount. A key capability f
arXiv:2609.01967v1 Announce Type: new Abstract: Data-driven process simulation aims to generate realistic case trajectories from historical event logs without requiring an explicitly specified model o
arXiv:2609.02107v1 Announce Type: cross Abstract: Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding