Where the reviewers can't agree
Video generation enables unified multimodal reasoning via Sora-2, which matches vision-language models and exceeds GPT-5 on spatial tasks while scoring 92% on MATH.
Published Nov 6, 2025 · 0 citations · ▲ 242 on Hugging Face · Code ★ 319
Only vote on papers you've read. Sign in with GitHub to vote.
RIDE extrapolates RL-induced representation residuals for stable on-policy distillation, surpassing output-space methods and matching or exceeding RL teachers.
Published Sep 29, 2026 · 0 citations · ▲ 577 on Hugging Face · Code ★ 6
Only vote on papers you've read. Sign in with GitHub to vote.
On-policy power distillation trains models to generate sharpened answers directly, improving single-sample math reasoning by up to 27.3 points and outperforming multi-candidate sampling and reward-based methods.
Published Oct 5, 2026 · ▲ 4 on Hugging Face · Code ★ 1
Only vote on papers you've read. Sign in with GitHub to vote.
AFP-GIC transfers adaptive fused priors from a frozen pretrained model to guide generative compression without transmitting them, reducing decoder latency and parameters while improving very-low-bitrate naturalness.
Published May 16, 2026 · ▲ 4 on Hugging Face · Code ★ 4
Only vote on papers you've read. Sign in with GitHub to vote.
Deepfake detectors degrade to 76% accuracy and near-zero under attacks, so calibrated reconstruction-based authentication bounds false real-image certification to 1%.
Published Oct 5, 2026 · ▲ 13 on Hugging Face · Code ★ 2
Only vote on papers you've read. Sign in with GitHub to vote.
Frozen and fine-tuned TabPFN representations for tabular anomaly detection yield ZEN and FOCUS, surpassing all ADBench baselines in AUROC despite unsupervised deployment and contaminated reference sets.
Published Oct 5, 2026 · ▲ 5 on Hugging Face · Code ★ 1
Only vote on papers you've read. Sign in with GitHub to vote.
LoHi trades per-frame resolution for denser temporal sampling via low-resolution streams plus sparse high-resolution frames, boosting long-video accuracy up to 10.6 points and cutting front-end latency up to 7x.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published Oct 3, 2026 · ▲ 13 on Hugging Face
Only vote on papers you've read. Sign in with GitHub to vote.
PerturbBot breaks vision-language-action shortcut priors via perturbative training while GroundingFscore diagnoses shortcut reliance, enabling healthier scaling without altering inference.
Published Oct 3, 2026 · ▲ 13 on Hugging Face · Code ★ 6
Only vote on papers you've read. Sign in with GitHub to vote.
APO learns shared LLM aligner initializations via grouped gradient coordination to enable few-shot personalization under heterogeneous preferences and scarce feedback, improving over baselines with 20 local examples.
Published Oct 5, 2026 · ▲ 5 on Hugging Face
Only vote on papers you've read. Sign in with GitHub to vote.
Learned latent protein languages improve autoregressive generation scaling, speed, and quality versus amino-acid and coordinate token models.
Published Oct 2, 2026 · ▲ 5 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
PaLoRA derives an optimal rank-aware pacing law for LoRA continual learning that adaptively restricts gradient scaling to prevent forgetting, improving long-horizon benchmark accuracy by 4%.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published Oct 3, 2026 · ▲ 9 on Hugging Face · Code ★ 2
Only vote on papers you've read. Sign in with GitHub to vote.
RealtimeWAM uses teacher-anchored consistency distillation and cross-expert wavefront pipelining for one-step asynchronous action generation, achieving near-lossless performance with ~25x speedup.
Published Oct 5, 2026 · ▲ 12 on Hugging Face · Code ★ 2,880
Only vote on papers you've read. Sign in with GitHub to vote.
Code2Games coordinates scene analysis and gameplay planning via shared representations to generate consistent gaming worlds and adapt them to Unreal Engine 5. The framework improves visual quality, interactive fidelity, and playable-game quality over direct coding-agent generation on the GameCode4D
Published Oct 4, 2026 · ▲ 6 on Hugging Face · Code ★ 4
Only vote on papers you've read. Sign in with GitHub to vote.
CARPM-FIQA accumulates relative point margin scores across training epochs to stabilize face image quality estimates, reducing variance and improving ranking stability near top performance.
Published Sep 15, 2026 · ▲ 6 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Distilling private health records into a released scoring tool enables agentic discovery of CBC biomarkers that improve diagnostic AUC over literature baselines without exposing patient data.
Published Oct 3, 2026 · ▲ 4 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
CurveCodec 2 predicts quantized skeletal curves from past values and learns residual entropy models to reduce animation storage to 0.22-0.37x of ACL with verified error bounds.
Published Oct 3, 2026 · ▲ 4 on Hugging Face · Code ★ 5
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
FairRSFM benchmarks remote sensing foundation models by biome to expose hidden ecological performance disparities and tests debiasing methods without backbone updates. Aggregate metrics consistently mask large biome-dependent gaps, though mitigation effectiveness varies by model and task.
Published Oct 5, 2026 · ▲ 5 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
UndoBench separates tool-using agent competence from fault recovery via paired enterprise workflow trials, finding 83.54% nominal success but only 46.72% recovery success with phase-dependent vulnerabilities.
Published Oct 4, 2026 · ▲ 11 on Hugging Face · Code ★ 1
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Periscope arranges text chunks in a grid to build an evidence map via local and strided probes, letting frozen language models answer questions across multi-million-token contexts with sublinear cost and small GPU memory.
Published Oct 2, 2026 · ▲ 8 on Hugging Face · Code ★ 1
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
SEER uses self-evolving event reasoning and retrieval to dynamically optimize forecasting with exogenous events via reflective memory and causal knowledge, outperforming state-of-the-art baselines.
Published Oct 2, 2026 · ▲ 13 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ADSD links numerical diagnosis to reusable solver self-improvement, reducing mean solver error by nearly 71x across four challenging numerical domains.
Published Oct 2, 2026 · ▲ 8 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
UnAct uses gradient-free targeted activation interventions to unlearn model classes from few forget images without gradients, labels, or retained data, matching or exceeding SSD and LFSSD accuracy across datasets and preventing network collapse with scarce data.
Published Oct 3, 2026 · ▲ 4 on Hugging Face · Code ★ 1
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Fixing initial token cues in base models boosts reasoning to match RL performance, with effects traced to training data associations that can be causally edited.
Published Oct 5, 2026 · ▲ 12 on Hugging Face · Code ★ 2
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
The RA-Bench benchmark reveals current detectors fail to consistently identify AI-generated crisis videos, which become harder to detect after social dissemination and frequently mislead humans.
Published Aug 14, 2026 · 0 citations · ▲ 287 on Hugging Face · Code ★ 132
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ACG-Bench evaluates arm-wise compositional generalization in dual-arm vision-language-action models via AE-VLA, which achieves 21.53% simulated and 39% real-world success versus under 6% baselines.
Published Oct 5, 2026 · ▲ 4 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Split-language-model gradients boost token recovery to 97.38% and document reconstruction to 37.77%, so split traffic requires per-token and per-document leakage reporting.
Published Oct 2, 2026 · ▲ 8 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
StudentSim trains LLM student simulators via pooled training and per-student specialization, outperforming GPT-5.4 on behavioral fidelity and guidance responsiveness across chess, writing, and math.
Published Sep 1, 2026 · 0 citations · ▲ 495 on Hugging Face · Code ★ 53
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Empirical Variational Autoencoder learns autoregressive latent priors empirically via one linear layer to close the VAE prior-posterior gap, yielding high-fidelity sequential generation competitive with diffusion models at much faster inference.
Published Oct 5, 2026 · ▲ 7 on Hugging Face · Code ★ 4
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
SHIFT predicts harness utility via a local LLM to search multi-agent structures per query, achieving ~80% mean accuracy across benchmarks while reducing execution tokens by 32%.
Published Oct 2, 2026 · ▲ 10 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HLA-WM combines geometry-guided retrieval with recurrent linear attention to fix long-range forgetting in video world models, improving 60-second consistency metrics by up to 28.5% with 12× lower memory and no retraining.
Published Oct 5, 2026 · ▲ 6 on Hugging Face · Code ★ 2
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
InterMimicGen retargets human motion capture to humanoids and self-evolves tracking data via iterative simulation-verified augmentation to scale dexterous loco-manipulation.
Published Oct 5, 2026 · ▲ 4 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
FLaRe uses flow matching for latent reasoning that is useful, diverse, explainable, refinable and efficient, reaching 97% of explicit chain-of-thought accuracy at 25% latency.
Published Oct 5, 2026 · ▲ 10 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Systematizing 139 semantic decision engine families reveals most miss network deadlines and verification, with only four reporting deadline attainment; unverified decisions reverse admission verdicts under queued execution, prompting minimum reporting rules and a research agenda.
Published Oct 5, 2026 · ▲ 6 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Prior-Fitted Language Model, trained solely on synthetic non-linguistic data, learns to infer and predict real languages from context with frozen weights, achieving strong cross-lingual compression and reasoning without ever seeing real text.
Published Oct 5, 2026 · ▲ 7 on Hugging Face · Code ★ 1
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
RACE predicts subskill transition timing to extend VLA action chunks reliably, reducing stop-and-go idle time ~5x on real robots while improving success rates.
Published Oct 5, 2026 · ▲ 13 on Hugging Face · Code ★ 3
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
RobotUse organizes robot computation, context, and decisions around revisable physical actions via visual target selection and persistent playbooks, achieving 45% RoboLab success and real-world learning.
Published Oct 4, 2026 · ▲ 14 on Hugging Face · Code ★ 4
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
RASO retrieves and adapts external skills via cross-harness adaptation to initialize and iteratively update agent skills, outperforming non-retrieval baselines across benchmarks.
Published Sep 29, 2026 · ▲ 63 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Agentic retrieval combining LLM reasoning with dense retrieval improves nDCG@10 by 8.7 points over standard retrieval but requires 107 seconds and 764K input tokens per query.
Published Oct 5, 2026 · ▲ 7 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Imagine3D-LLM learns compact scene representations via learnable summary tokens decoded into 3D Gaussian splatting with photometric loss, improving multi-view spatial reasoning benchmarks.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published Sep 29, 2026 · ▲ 72 on Hugging Face · Code ★ 37
Only vote on papers you've read. Sign in with GitHub to vote.
Speculative tool execution predicts tool calls from partial ASR to run them during speech, cutting median voice-agent response latency from 5.79 s to 4.60 s.
Published Oct 6, 2026 · ▲ 1 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
LoGRA reduces LLM reinforcement learning memory by up to 45.7% via low-rank gradient sketches and predicted-KL step control, enabling 27B-parameter training on single nodes.
Published Oct 5, 2026 · ▲ 11 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
QuantCode specializes LLMs for executable trading code via framework pretraining and validated fine-tuning, boosting backtest success to 83.5% while revealing specialization trade-offs in tool use and repair.
Published Sep 30, 2026 · ▲ 11 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
World editing intervenes on executable environments at increasing depth via IGMWorld and IGMBench, where top agents achieve 78.2% task success with reliability declining by depth.
Published Oct 1, 2026 · ▲ 14 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Loop Flow Transformers loop a shared diffusion transformer with depth-indexed regression targets, improving generation with more inference compute and fewer parameters than dense models.
Published Oct 4, 2026 · ▲ 9 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Survey synthesizes code LLM development from data curation to autonomous agents, analyzes general and specialized models, and maps the research-practice gap to practical needs.
Published Nov 23, 2025 · 1 citation · ▲ 307 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HarnessDev evaluates LLMs creating and evolving agent harnesses, finding generated harnesses lag human references on coding and search but match them on writing and ML tasks, with unstable, model-dependent evolution gains.
Published Sep 1, 2026 · 0 citations · ▲ 566 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
PrisMem drives agent memory self-evolution via capability-specific guidance, dependency-aware selection, and trace-guided integration, outperforming baselines by up to 10.54 points on million-token benchmarks.
Published Oct 5, 2026 · ▲ 6 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Activation alignment trains a linear map to align partial-context student activations with full-context teacher activations, significantly improving tabular in-context learning efficiency and recovering much of the performance gap.
Published Oct 5, 2026 · ▲ 5 on Hugging Face · Code ★ 1
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ASCENT online test-time trains agents by self-distilling verified deployment trajectories into LoRA weights via a frozen hindsight model, improving long-horizon success and efficiency without external teachers or memory retrieval.
Published Oct 4, 2026 · ▲ 17 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
This survey reviews post-training and alignment strategies for video generation, framing them as implicit or explicit alignment across four methodological categories to improve controllability and reliability.
Published Sep 30, 2026 · ▲ 60 on Hugging Face · Code ★ 208
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ALIVE inserts objects that interact with video contents via first-frame editing and interaction guidance, outperforming baselines on interaction and insertion benchmarks.
Published Oct 6, 2026 · ▲ 3 on Hugging Face · Code
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HRM-Text replaces Transformers with a hierarchical recurrent model and trains on instruction pairs to achieve competitive 1B-parameter performance with 100, 900x fewer tokens and far less compute.
Published May 20, 2026 · 0 citations · ▲ 322 on Hugging Face · Code ★ 2,134
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Targeted bias injection via closed-loop activation steering exploits diffusion language model denoising trajectories to steer frozen models toward adversarial demographic answers with minimal corruption.
Published Oct 5, 2026 · ▲ 14 on Hugging Face · Code ★ 3
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
This survey explains large language model core concepts to numerical analysts and highlights key numerical linear algebra contributions to LLM techniques.
Published Oct 3, 2026 · ▲ 4 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
RepoExec benchmarks repository-level code generation, showing instruction-tuned models use cross-file contexts better despite pretrained LLMs achieving higher correctness.
Published Jun 17, 2024 · 3 citations · ▲ 12 on Hugging Face · Code ★ 164
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Dev-Primitives turn repository artifacts into active, resident-LLM agents with self-modification interfaces, and HERMES improves software engineering benchmarks by 12.4% over baselines while cutting inference costs by 26.2%.
Published Oct 6, 2026 · ▲ 2 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
StateM improves long-horizon agent accuracy via durable-state harness scaling without model changes, reaching 95.3% on Terminal-Bench 2.1 and cutting API costs to about $15 versus $574.68.
Published Aug 15, 2026 · 0 citations · ▲ 452 on Hugging Face · Code ★ 1,312
Only vote on papers you've read. Sign in with GitHub to vote.
Orca is a world foundation model that learns a unified latent space via next-state prediction from video and language, enabling scalable text, image, and action generation.
Published Jun 29, 2026 · 0 citations · ▲ 511 on Hugging Face · Code ★ 1,021
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HiPLEX factorizes full-duplex speech policies into timing and content controllers to jointly optimize interaction dynamics via reinforcement learning. It lowers takeover rates, reduces interruption latency, and improves human-like turn timing versus GRPO.
Published Oct 6, 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
DiVeR improves verifier-guided VLA test-time scaling by reweighting learning toward decision-critical states using action representation dispersion, boosting success without extra annotations or overhead.
Published Oct 4, 2026 · ▲ 1 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ActiveSaddler automates curriculum learning for agent harness optimization via non-stationary bandits that adapt training scenarios to evolving failure patterns, boosting Pass@1 by 4.4, 7.5 points.
Published Oct 1, 2026 · ▲ 82 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Vidu S2 enables real-time interactive avatar and editing video generation at 720p with dynamic references and spatial capabilities, outperforming all baselines.
Published Sep 10, 2026 · 0 citations · ▲ 706 on Hugging Face · Code ★ 501
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
SaCRL jointly identifies causal structure and learns invariant representations via soft optimization over HSIC-based invariance violations without prior structural knowledge. It guarantees structure identification, invariance satisfaction, and out-of-distribution generalization while achieving state
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
POTER uses optimal transport geometry between training and reference distributions to downweight mislabeled or shortcut-aligned samples, achieving state-of-the-art worst-group accuracy with a single training stage.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Cog-VADU reformulates video anomaly detection as sequential cognitive reasoning via recurrent chain-of-thought prompting and cross-modal re-ranking for training-free zero-shot performance.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
MoLF dynamically routes optimizer updates between full fine-tuning and LoRA to match or beat the stronger static method across tasks, and its efficient variant surpasses AdaLoRA and AdaMix by up to 11.70 points.
Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
HelixWorld is a real-time interactive audio-visual world model that synchronizes visual scenes and spatial stereo sound under user control at 24 FPS, surpassing silent models in acoustic immersion.
Published Sep 29, 2026 · 0 citations · ▲ 32 on Hugging Face · Code ★ 623
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Utonia trains a single self-supervised point transformer encoder across diverse point cloud domains to learn unified representations that improve cross-domain perception, embodied reasoning, and robotic manipulation.
Published Mar 3, 2026 · 0 citations · ▲ 189 on Hugging Face · Code ★ 755
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
LLM2Jev extracts calibrated Jev-style decisions from LLM token probabilities via training-free inference or tree-factorized fine-tuning, showing strong 4B models already match specialized decision models while fine-tuning mainly helps weaker backbones and specific tasks without degrading generation.
Published Oct 1, 2026 · 0 citations · ▲ 6 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Separating domain volatility from observation surprise via composite homeostatic-allostatic gates improves recency-shift detection and limits false updates, with linking and verification dominating memory errors.
Published Apr 28, 2025 · 7 citations · ▲ 73 on Hugging Face · Code ★ 66,670
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
BDA treats multi-LLM council moves as observations of a per-agent reliability model to yield calibrated answer probabilities and robustly handle persistent adversaries without extra LLM calls.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Kronos pre-trains a financial time-series foundation model on 12 billion K-line records via specialized tokenization, achieving major gains in zero-shot forecasting, volatility prediction, and synthetic data generation.
Published Aug 2, 2025 · ▲ 58 on Hugging Face · Code ★ 40,075
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
PDE-JEPA introduces predictive masked-latent pretraining with geometry projection and structured latent predictors for parametric PDE dynamics, reducing errors by 33.4% in-distribution and 51.4% on unseen parameters.
Published Sep 28, 2026 · 0 citations · ▲ 53 on Hugging Face · Code ★ 9
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Hybrid Linear Attention introduces query-dependent chunk-level routing for Gated DeltaNet, improving long-context benchmarks by up to 5.57 points via adaptive recurrent memory composition.
Published Oct 5, 2026 · ▲ 2 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
COVID-19 Instagram exposure significantly raises student anxiety, which mediates increased panic buying intentions among Bandung students.
Published Dec 27, 2023 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Multilingual GSM-Symbolic introduces matched math problems across 15 languages to show model size, resource level, reasoning, and typology determine cross-lingual transfer, with size and reasoning closing low-resource gaps but not typological ones.
Published Oct 2, 2026 · 0 citations · ▲ 47 on Hugging Face · Code ★ 4
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
OpenART scales agent red teaming via open-ended environment evolution across 10,000 stateful scenarios, with EMHA achieving 85% attack success that grows with complexity.
Published Aug 1, 2026 · 0 citations · ▲ 266 on Hugging Face · Code ★ 231
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Spatial Memory Intelligence introduces understanding-driven atomic operations for spatial-memory management in long-video world models, improving sparsity, stability, and spatial consistency.
Published Oct 1, 2026 · 0 citations · ▲ 49 on Hugging Face · Code ★ 19
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Flexible Flows for Biological Sequence Design proposes structured couplings and latent edit-based rate parameterization to achieve state-of-the-art results across diverse biological sequence generation tasks.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ReaLVR fixes latent reasoning's weak visual grounding by supervising latent tokens with visual evidence, improving reasoning across scales up to 235B.
Published Sep 28, 2026 · 0 citations · ▲ 217 on Hugging Face · Code ★ 40
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
MinerU2.5 decouples global layout analysis from local content recognition via coarse-to-fine parsing, achieving state-of-the-art document parsing accuracy with low computational overhead.
Published Sep 26, 2025 · ▲ 180 on Hugging Face · Code ★ 81,154
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
SmoothOperator modulates per-sample label smoothing via embedding prominence to reduce over-alignment, boosting open-set recognition AUROC by up to 4.7%.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Context language models treat context as self-modified files to learn context management, outperforming external strategies with lower compute and enabling in-context and parametric learning of management strategies.
Published Sep 29, 2026 · 0 citations · ▲ 40 on Hugging Face · Code ★ 571
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Software-in-the-loop reconstruction scales terminal-agent training by deriving verified tasks from existing scientific workflows without manual references, improving Terminal-Bench 2 performance to 53.56%.
Published Oct 2, 2026 · 0 citations · ▲ 10 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Embodied progress reward models fail at long tasks due to missing context, but ProgressCompass supplies needed context to cut progress estimation errors by up to 82%.
Published Sep 29, 2026 · 0 citations · ▲ 11 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
A typed settlement contract audits concurrent LLM agent actions, showing joint policies complete 59% more six-agent doorway tasks than conservative rejection, with exact replay of 156 checkpoints and rejection of 1,332 corruptions.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Pretrained ASR backbones enable training-free wake-word detection, and PCA-based pruning retains performance at 50% encoder reduction.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Kandinsky 6.0 Video introduces diffusion models that generate synchronized 5-second audio-video clips with lip-sync via a dual-stream CrossDiT architecture, with the 29B-parameter Pro version outperforming its predecessor and matching top competitors in speech quality.
Published Oct 4, 2026 · ▲ 113 on Hugging Face · Code ★ 119
Only vote on papers you've read. Sign in with GitHub to vote.
Post-training multi-token prediction heads on ~2.5B chain-of-thought tokens match pretraining speedups with 10^3-10^4x less data, while chain-aware verification and adaptive head selection boost throughput up to 16%.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Collective Bias Mitigation routes queries among diverse LLMs and fosters collaboration to substantially reduce bias over single-model baselines.
Published Oct 2, 2026 · 0 citations · ▲ 14 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
GTR replaces softmax attention with gated token recurrence for efficient high-resolution dense prediction, achieving 58.9 COCO box AP with low latency.
Published Sep 22, 2026 · 0 citations · ▲ 12 on Hugging Face · Code ★ 50
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
World Embedding Benchmark evaluates physical encoding via 8,000 simulation cases, finding alignment trades off against quantitative recoverability and retrieval improves video generation fidelity.
Published Oct 2, 2026 · 0 citations · ▲ 44 on Hugging Face · Code ★ 4
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
REdit reshapes LLM neural circuits before editing to reduce reasoning-pattern interference, improving generality and locality over broad training baselines.
Published Jan 25, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Yo-ByT5 is a byte-level Yorùbá diacritic restoration model matching mT5-base accuracy with half the parameters and superior text fidelity.
Published Oct 1, 2026 · 0 citations
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
TTCS uses a co-evolving question synthesizer and reasoning solver to build test-time curricula that stabilize self-updates and improve reasoning on hard math benchmarks.
Published Jan 30, 2026 · 0 citations · ▲ 35 on Hugging Face · Code ★ 53
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
CacheBack uses receiver-conditioned filtering of sender KV caches via attention weights to cut transferred state by 75%, boosting multi-agent accuracy by 14.7 points and reducing latency 3.2x versus text.
Published Sep 25, 2026 · 0 citations · ▲ 11 on Hugging Face · Code ★ 6
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
MotorMind connects general vision-language models to deterministic robot control via mid-level actions and feedback loops, achieving 66.7% zero-shot success on LIBERO-PRO and 95% on real robots without task-specific training or external tools.
Published Sep 29, 2026 · 0 citations · ▲ 90 on Hugging Face
Only vote on papers you've read. Sign in with GitHub to vote.
Parallel-R1 uses a progressive curriculum combining supervised warmup and reinforcement learning to train large language models in parallel reasoning, achieving significant gains on math benchmarks by treating parallel thinking as a temporary exploration scaffold that unlocks higher final performanc
Published Sep 9, 2025 · 0 citations · ▲ 105 on Hugging Face · Code ★ 265
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
SearchJev is a fast calibrated System-1 model that scores search decisions directly without autoregressive generation, improving decision quality, speed, and calibration over same-size language models.
Published Oct 4, 2026 · ▲ 14 on Hugging Face · Code ★ 4
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Principia benchmarks video generators via calibration-independent relational physics consistency across eight Newtonian phenomena, finding top models score below 0.42 despite high VBench ratings.
Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 18 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.