Showing papers from Technische Universität München Show all papers
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.
Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 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.
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 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.
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.
Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 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.
Multi-variable conformal prediction extends calibration to vector-valued scores with multiple variables, removing data splitting while preserving coverage and yielding smaller, more stable prediction sets.
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.
Diffusion LLMs amortize adversarial prompt optimization by directly generating diverse, transferable jailbreak prompts that bypass black-box target models.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · 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.
L2P transfers pre-trained latent diffusion models to pixel space via frozen intermediate layers and synthetic data, enabling efficient 4K generation with near-source performance.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 36 on Hugging Face · Code ★ 195
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.
CapTrack defines LLM post-training forgetting as systematic behavioral drift rather than only factual loss, finding instruction tuning causes the strongest drift and no universal mitigation exists.
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.
MedKIT evaluates medical LLM knowledge integration via clinical updates, revealing strong recall but limited relational, compositional, and operational generalization across 12 strategies.
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.
Extending a manifold triangulation benchmark reveals GNNs and HOMP can saturate it with proper representations, yet existing models fail to generalize beyond combinatorial structure.
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.
APM benchmark evaluates LLM style personalization via hidden arbitrary preference mappings, finding routing most reliable while RAG and soft prompts show limited gains.
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.
Joint Self-Improvement uses a joint generative-predictive model and self-improving sampling to reduce distribution shift and efficiently generate optimized molecules under limited evaluation budgets.
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.
Freezing cohort INR layers at highest stable-rank depth improves fitting, with sparse autoencoders revealing SIREN learns localized atoms and FFMLP learns image-spanning memorized contours.
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.
KV Packet treats cached documents as immutable packets with lightweight trainable adapters to eliminate KV cache recomputation, achieving near-zero FLOPs and lower TTFT with comparable F1.
Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 10 on Hugging Face · Code ★ 39
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.
Noiseless inverse optimization achieves tight O(d/T) generalization and regret bounds, with parameter-free algorithms matching adversarial lower bounds.
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.