Knowledge catalogue
arXiv:2610.03403v1 Announce Type: cross Abstract: Forest point cloud segmentation is fundamental for fine-grained 3D forest scene understanding, yet remains challenging due to irregular tree structure
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:2610.02799v1 Announce Type: new Abstract: Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely
arXiv:2610.02816v1 Announce Type: new Abstract: Linear attention models have emerged as efficient alternatives to standard attention, but effectively managing their fixed-size recurrent memory remains
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
arXiv:2606.19617v2 Announce Type: replace Abstract: We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image decoding. The im
arXiv:2610.02232v1 Announce Type: cross Abstract: Predicting phenotypic and transcriptional responses to perturbations at single-cell resolution provides a powerful tool for probing biological systems
arXiv:2610.02697v1 Announce Type: cross Abstract: Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructi
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:2610.02373v1 Announce Type: cross Abstract: GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that deter
arXiv:2610.02772v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect
arXiv:2610.03120v1 Announce Type: new Abstract: Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to driftin
arXiv:2610.02396v1 Announce Type: cross Abstract: Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficul
arXiv:2602.00066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constrai
arXiv:2610.03380v1 Announce Type: new Abstract: Deepfake detection in videos remains challenging, as manipulated content may appear visually consistent at the frame level while exhibiting subtle tempo
arXiv:2610.03296v1 Announce Type: new Abstract: Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parall
arXiv:2610.03137v1 Announce Type: new Abstract: Specifying a goal in language rather than as a goal frame is a natural interface for planning with a latent world model, but testing it needs scenes in
arXiv:2610.02943v1 Announce Type: new Abstract: Multimodal 3D Human Pose Estimation (3D HPE) combines complementary information from RGB, LiDAR, and mmWave radar, but models trained on correlated obse
arXiv:2610.03161v1 Announce Type: cross Abstract: Feature selection for imbalanced classification tasks such as credit card fraud and consumer default detection requires balancing predictive relevance
arXiv:2610.02665v1 Announce Type: cross Abstract: Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajecto
Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modified harness matched Codex for 4.03. Specifically, a coding
arXiv:2610.02700v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal
arXiv:2610.02918v1 Announce Type: cross Abstract: Jazz pianists develop distinctive traits that experienced listeners can often identify within seconds, yet the features underlying this recognition re
arXiv:2610.03702v1 Announce Type: new Abstract: The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular appr
arXiv:2610.02359v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-qual
arXiv:2610.03636v1 Announce Type: cross Abstract: Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistenc
arXiv:2610.03258v1 Announce Type: cross Abstract: Scalable nonlinear causal discovery requires methods that combine flexible mechanism estimators with efficient search over large graph spaces. Several
arXiv:2610.02824v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requiremen
arXiv:2610.03716v1 Announce Type: new Abstract: Dense 3D point tracking has been a prominent paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pix
arXiv:2610.02283v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) provides a parameter-efficient approach to continual learning, but its nominal rank can conceal a loss of effective adaptatio
arXiv:2610.02249v1 Announce Type: new Abstract: It has recently been shown that nearest-neighbour retrieval provides a strong baseline for molecular fingerprint prediction from MS/MS spectra, with sev
arXiv:2610.03551v1 Announce Type: new Abstract: Large language models (LLMs) have reached expert-level performance on competition mathematics largely through the volume of search placed around them: c
arXiv:2610.02388v1 Announce Type: new Abstract: Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes s
arXiv:2610.02632v1 Announce Type: new Abstract: As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintai
arXiv:2610.03125v1 Announce Type: cross Abstract: Speech delivery varies with both the requested paralinguistic attribute and the linguistic content. We introduce ParaGeo, a matched-content decomposit
arXiv:2610.02569v1 Announce Type: cross Abstract: Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-im
arXiv:2610.03665v1 Announce Type: cross Abstract: Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a di
arXiv:2610.03192v1 Announce Type: new Abstract: Mobile Gaussian reconstruction must satisfy two requirements: the reconstruction model must execute within a device resource envelope, and the resulting
arXiv:2610.02511v1 Announce Type: new Abstract: Advancements in high-resolution numerical weather prediction (NWP) and data assimilation (DA) have shaped the developments in deep learning (DL) archite
arXiv:2610.03326v1 Announce Type: new Abstract: Diffusion language model (dLLM) compression faces a known challenge because calibration is typically performed on clean, fully visible activations, wher
arXiv:2610.03664v1 Announce Type: new Abstract: Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive para
arXiv:2610.02413v1 Announce Type: new Abstract: LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hid
arXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language
Hey all. We've spent the last weeks getting Qwen3.8-Flash-Next (125B MoE, 6B active) to run properly on one AMD Strix Halo box (Ryzen AI Max+ 395, 128 GB). Tonight we're releasing both the 95 GB EXL3
arXiv:2601.22352v2 Announce Type: replace-cross Abstract: Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation.
arXiv:2610.02976v1 Announce Type: new Abstract: Audio-Visual Large Language Models (AV-LLMs) remain prone to cross-modal hallucinations, where one modality incorrectly affects predictions about anothe
arXiv:2610.03022v1 Announce Type: cross Abstract: Simultaneous Sign Language Translation (SLT) is critical for real-time communication, yet existing methods remain largely confined to sentence-level,
arXiv:2610.02368v1 Announce Type: new Abstract: Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordin
arXiv:2610.02887v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) suffer from hallucinations, creating a critical need for Uncertainty Quantification (UQ) to ensure reliable d
arXiv:2610.02217v1 Announce Type: cross Abstract: Large sparse linear systems from PDE discretizations require correction subspaces whose operator images explain the current residual. We study this re
arXiv:2610.03054v1 Announce Type: new Abstract: Clustered Federated Learning (FL) partitions a client population into groups of similar local distributions and trains one specialized model per cluster
arXiv:2610.02708v1 Announce Type: new Abstract: Wet-lab experimentation serves as the gold standard for hypothesis verification in scientific discovery; yet it is inherently labor-intensive, costly, a
arXiv:2610.03303v1 Announce Type: new Abstract: Uncertainty quantification (UQ) for random partial differential equations (PDEs) is ubiquitous in computational science and engineering. However, classi
arXiv:2610.03132v1 Announce Type: cross Abstract: Generative planners based on diffusion/flow matching can learn to synthesize long-horizon trajectories from demonstrations. However, real-world deploy
arXiv:2610.02981v1 Announce Type: new Abstract: Source-Free Domain Adaptation (SFDA) aims to adapt a source-pretrained model to an unlabeled target domain without access to the original source domain.
arXiv:2610.03372v1 Announce Type: new Abstract: Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards
arXiv:2610.02343v1 Announce Type: new Abstract: Geometric understanding supports endoscopic navigation and robotic assistance, but learning reliable endoscopic geometry faces two challenges: scarce ge
arXiv:2610.02324v1 Announce Type: cross Abstract: Foundation multimodal large language models are designed to support a broad spectrum of capabilities across diverse domains. Multi-teacher on-policy d
arXiv:2610.03029v1 Announce Type: new Abstract: Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological
arXiv:2610.02521v1 Announce Type: new Abstract: Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observatio