Showing papers from Facebook Show all papers
Atlanta Poster Session 2, Wed, Dec 9, 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.
Atlanta Poster Session 6, Fri, Dec 11, 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.
Atlanta Poster Session 2, Wed, Dec 9, 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.
Atlanta Poster Session 6, Fri, Dec 11, 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.
Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 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.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · 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.
Sydney Poster Session 1, Tue, Dec 8, 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.
Atlanta Poster Session 6, Fri, Dec 11, 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.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 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.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · 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.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 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.
Parallel-Synthesis lets LLM synthesizers consume parallel agents' KV caches directly via a cache mapper and adapter, matching text synthesis on seven of nine benchmarks while cutting time-to-first-token by 2.5x-11x.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 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.
Post-training quantization of reasoning models increases chain-of-thought length and overthinking errors without improving accuracy, yet penalizing overthinking markers reduces reasoning cost and fixes failures.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 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.
DREAM unifies contrastive and generative objectives via Masking Warmup, yielding joint visual understanding gains and faster, higher-quality text-to-image generation.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 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.
RepFusion conditions a diffusion transformer on multimodal LLM outputs to denoise visual representations, outperforming comparable newly initialized denoisers.
Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 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.
RigidFormer is a transformer that learns mesh-free rigid-body dynamics via object-level anchors and differentiable Kabsch projection, outperforming mesh-based baselines with faster inference and scalability to 200+ objects.
Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 93
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.
DARLING uses a learned partition function to jointly optimize language model response quality and semantic diversity via reinforcement learning, improving both quality and novelty across creative and math benchmarks.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 25 on Hugging Face · Code ★ 61
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.
Medical imaging pretraining reveals asymmetric cross-domain scaling and power-law transfer, yielding optimized data allocations with a hub-and-island structure that improves transfer over proportional sampling by up to 58%.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.
ECHO-2 is a distributed RL framework that overlaps rollout generation, dissemination, and training with bounded policy staleness to improve cost efficiency while preserving rewards.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 13 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 two-stage adapter embeds foundation model predictions into a constrained multinomial logit, guaranteeing cost monotonicity and valid value-of-time estimates while improving choice accuracy by up to 12.8 percentage points.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 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.
TextSeal is a localized LLM watermark using dual-key generation and entropy-weighted scoring for robust provenance and distillation detection without inference overhead.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 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.
HiLight trains a lightweight actor via reinforcement learning to insert highlight tags around pivotal evidence spans in frozen LLM contexts, boosting reasoning without altering inputs or requiring evidence labels.
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 5 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 1MB replay script outperforms frontier agents on static benchmarks because of flawed environment design and evaluation; the paper proposes PRISM principles, DigiWorld, and hierarchical bootstrap aggregation to fix both.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 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.
MAGE uses block-diffusion's aligned all-[MASK] queries to select reusable sparse KV subsets, achieving near-lossless accuracy with up to 6.82x speedup at 128K context.
Sydney Poster Session 3, Wed, Dec 9, 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.
Schema-derived ODS constraints enable small LMs to match or exceed 15B, 34B models on structural MLIR dialects at 8, 25× speed without retraining, though attribute-heavy dialects remain challenging.
Atlanta Poster Session 6, Fri, Dec 11, 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.
RANSAC scoring analytically marginalizes inlier scale via a conjugate prior, yielding a parameter-free score that outperforms threshold-based methods across data regimes with O(N log N) computation.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.
Residual Quantization maps contexts to discrete additive codes enabling nonlinear contextual bandits with strictly bounded memory, beating linear variants on 11 of 13 datasets and matching heavy retrained baselines with up to 1000x less memory.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.
TRIBE v2 synthetic fMRI augmentation improves brain-to-image decoding by up to 68%, though optimal synthetic-to-real ratios vary by dataset, and synthetic-only training achieves above-chance zero-shot decoding.
Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · 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.
GRPO for LLM recommenders maximizes AUC but beam-search negatives reshape objectives toward partial AUC; proposed WPAUC with TAWin optimization improves top-K alignment and achieves state-of-the-art results.
Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · 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.
PISCO enables precise video instance insertion via sparse keyframe control while preserving dynamics, achieving monotonic gains with added signals and outperforming editing baselines.
Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 13 on Hugging Face · Code ★ 62
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.
MemReward propagates rewards through a heterogeneous rollout graph to enable LLM reinforcement learning using only 20% ground-truth labels and achieves over 96% of oracle performance.
Sydney Poster Session 1, Tue, Dec 8, 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.
Watermarking lacks enforceable standards and audit infrastructure, so current implementations serve as symbolic compliance rather than effective AI oversight.
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.
SWE-Protégé trains small language models to selectively seek expert guidance and avoid looping, achieving 42.4% Pass@1 on SWE-bench Verified with minimal expert use.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 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.
MetaCanvas enables multimodal LLMs to plan directly in diffusion latent spaces, outperforming global-conditioning baselines across six precise visual generation tasks.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 15 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.
TerminalWorld automatically builds terminal benchmarks from wild recordings, yielding 1,530 tasks where top agents achieve only 62.5% success with weak correlation to expert benchmarks.
Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 8 on Hugging Face · Code ★ 48
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.
VeriContest introduces 946 competitive programming problems with verified Rust specifications and proofs, showing state-of-the-art models reach only 5.29% on end-to-end verifiable generation.
Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 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.