Showing papers from Technion - Israel Institute of Technology, Technion Show all papers
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 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.
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.
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.
The FACTS Leaderboard benchmarks large language model factuality across multimodal, parametric, search, and grounding tasks via automated judges.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 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.
MulTaBench benchmarks 40 multimodal tabular datasets and shows target-aware tuning of text and image embeddings improves predictive performance over frozen embeddings.
Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026 · ▲ 142 on Hugging Face
Only vote on papers you've read. Sign in with GitHub to vote.
Under structured cross-modal nuisance correlation, cross-modal alignment and prediction have complementary failure modes partitioned by separation ratios into four regimes, with a data-driven procedure identifying preferred objectives and when neither beats single-modality baselines.
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.
Applying CVaR to the immediate belief cost targets per-step state uncertainty while preserving standard MDP structure, enabling any expectation-based planner to become risk-sensitive with unchanged algorithms and end-to-end finite-time guarantees.
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.
KV-compressibility is a learnable property, so KV-CAT trains transformers via masked KV slots to yield representations more amenable to post-hoc compression without sacrificing quality.
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.
SP-CACW minimizes an upper bound on a target client's convergence error via convergence-aware weighting that trades peer bias against variance and excludes harmful peers.
Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 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.
VideoMDM trains 3D human motion diffusion models solely from 2D video poses via depth-weighted reprojection, nearly matching fully 3D-supervised quality without ground-truth 3D data.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 22 on Hugging Face · Code ★ 58
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.
For every k, k-WL fails to distinguish some non-isomorphic simple-spectrum graphs, so PRiSM provides the first complete canonicalization of their eigendecompositions to enable universal approximation.
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.
A framework combines multi-armed bandits with low-rank predictions to build doubly robust estimators and valid confidence intervals for identifying the best LLM with fewer evaluations.
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.
A single sensory-prediction recurrent network with Dale's Law co-emerges grid and place cells without supervision, reproducing key spatial coding phenomena.
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.
PolyTopoBench benchmarks vector polygon generation from remote sensing images, finding existing methods fail on complex multi-ring topologies with holes.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 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.